Automatically fetches the latest arXiv papers on VLN · VLA · SLAM · 3D · Embodied AI
This project automatically fetches the latest papers from arXiv based on predefined keywords.
- Each section in the README corresponds to a search keyword.
- Only the most recent papers are kept (up to 100 per keyword).
- Click Watch (👀) on the repo to get daily email notifications.
Last update: 2025-12-09
| Title | Date | Abstract | Comment |
|---|---|---|---|
| FALCON: Actively Decoupled Visuomotor Policies for Loco-Manipulation with Foundation-Model-Based Coordination | 2025-12-04 | ShowWe present FoundAtion-model-guided decoupled LoCO-maNipulation visuomotor policies (FALCON), a framework for loco-manipulation that combines modular diffusion policies with a vision-language foundation model as the coordinator. Our approach explicitly decouples locomotion and manipulation into two specialized visuomotor policies, allowing each subsystem to rely on its own observations. This mitigates the performance degradation that arise when a single policy is forced to fuse heterogeneous, potentially mismatched observations from locomotion and manipulation. Our key innovation lies in restoring coordination between these two independent policies through a vision-language foundation model, which encodes global observations and language instructions into a shared latent embedding conditioning both diffusion policies. On top of this backbone, we introduce a phase-progress head that uses textual descriptions of task stages to infer discrete phase and continuous progress estimates without manual phase labels. To further structure the latent space, we incorporate a coordination-aware contrastive loss that explicitly encodes cross-subsystem compatibility between arm and base actions. We evaluate FALCON on two challenging loco-manipulation tasks requiring navigation, precise end-effector placement, and tight base-arm coordination. Results show that it surpasses centralized and decentralized baselines while exhibiting improved robustness and generalization to out-of-distribution scenarios. |
|
| MDE-AgriVLN: Agricultural Vision-and-Language Navigation with Monocular Depth Estimation | 2025-12-03 | ShowAgricultural robots are serving as powerful assistants across a wide range of agricultural tasks, nevertheless, still heavily relying on manual operations or railway systems for movement. The AgriVLN method and the A2A benchmark pioneeringly extend Vision-and-Language Navigation (VLN) to the agricultural domain, enabling a robot to navigate to a target position following a natural language instruction. Unlike human binocular vision, most agricultural robots are only given a single camera for monocular vision, which results in limited spatial perception. To bridge this gap, we present the method of Agricultural Vision-and-Language Navigation with Monocular Depth Estimation (MDE-AgriVLN), in which we propose the MDE module generating depth features from RGB images, to assist the decision-maker on reasoning. When evaluated on the A2A benchmark, our MDE-AgriVLN method successfully increases Success Rate from 0.23 to 0.32 and decreases Navigation Error from 4.43m to 4.08m, demonstrating the state-of-the-art performance in the agricultural VLN domain. Code: https://github.com/AlexTraveling/MDE-AgriVLN. |
|
| AIDEN: Design and Pilot Study of an AI Assistant for the Visually Impaired | 2025-12-02 | ShowThis paper presents AIDEN, an artificial intelligence-based assistant designed to enhance the autonomy and daily quality of life of visually impaired individuals, who often struggle with object identification, text reading, and navigation in unfamiliar environments. Existing solutions such as screen readers or audio-based assistants facilitate access to information but frequently lead to auditory overload and raise privacy concerns in open environments. AIDEN addresses these limitations with a hybrid architecture that integrates You Only Look Once (YOLO) for real-time object detection and a Large Language and Vision Assistant (LLaVA) for scene description and Optical Character Recognition (OCR). A key novelty of the system is a continuous haptic guidance mechanism based on a Geiger-counter metaphor, which supports object centering without occupying the auditory channel, while privacy is preserved by ensuring that no personal data are stored. Empirical evaluations with visually impaired participants assessed perceived ease of use and acceptance using the Technology Acceptance Model (TAM). Results indicate high user satisfaction, particularly regarding intuitiveness and perceived autonomy. Moreover, the ``Find an Object'' achieved effective real-time performance. These findings provide promising evidence that multimodal haptic-visual feedback can improve daily usability and independence compared to traditional audio-centric methods, motivating larger-scale clinical validations. |
|
| SeeNav-Agent: Enhancing Vision-Language Navigation with Visual Prompt and Step-Level Policy Optimization | 2025-12-02 | ShowExisting Vision-Language Navigation (VLN) agents based on Large Vision-Language Models (LVLMs) often suffer from perception errors, reasoning errors, and planning errors, which significantly hinder their navigation performance. To address these limitations, a novel VLN agent framework, named SeeNav-Agent, is proposed in this work. First, to reduce perception hallucinations of the visual module of the VLN agent, a dual-view Visual Prompt (VP) technique is introduced in the input space, which can also improve the agent's understanding of current spatial states. Subsequently, a novel step-level Reinforcement Fine-Tuning (RFT) method, Step Reward Group Policy Optimization (SRGPO), is designed for the post-training of VLN agents. In SRGPO, we first define verifiable process rewards for the navigation task, and then perform efficient step-level advantage estimation by randomly grouping different navigation steps. SRGPO provides dense reward signals for the reinforcement learning process of the VLN agent and enhances its planning capability. Experimental results on the EmbodiedBench Navigation benchmark indicate that by introducing the zero-shot VP module, the GPT-4.1 achieves a navigation success rate of 86.7%, surpassing the current best LVLM by approximately 20 percentage points (pp). Through post-training based on SRGPO, the Qwen2.5-VL-3B model reaches a navigation success rate of 72.3%, outperforming the best existing LVLM model by 5.6 pp. Moreover, compared to RFT algorithms such as GRPO and GiGPO, the proposed SRGPO demonstrates significant improvements in training stability, convergence efficiency, and generalization capability. |
12 pages,6 figures |
| ST-Booster: An Iterative SpatioTemporal Perception Booster for Vision-and-Language Navigation in Continuous Environments | 2025-12-02 | ShowVision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to navigate unknown, continuous spaces based on natural language instructions. Compared to discrete settings, VLN-CE poses two core perception challenges. First, the absence of predefined observation points leads to heterogeneous visual memories and weakened global spatial correlations. Second, cumulative reconstruction errors in three-dimensional scenes introduce structural noise, impairing local feature perception. To address these challenges, this paper proposes ST-Booster, an iterative spatiotemporal booster that enhances navigation performance through multi-granularity perception and instruction-aware reasoning. ST-Booster consists of three key modules -- Hierarchical SpatioTemporal Encoding (HSTE), Multi-Granularity Aligned Fusion (MGAF), and ValueGuided Waypoint Generation (VGWG). HSTE encodes long-term global memory using topological graphs and captures shortterm local details via grid maps. MGAF aligns these dualmap representations with instructions through geometry-aware knowledge fusion. The resulting representations are iteratively refined through pretraining tasks. During reasoning, VGWG generates Guided Attention Heatmaps (GAHs) to explicitly model environment-instruction relevance and optimize waypoint selection. Extensive comparative experiments and performance analyses are conducted, demonstrating that ST-Booster outperforms existing state-of-the-art methods, particularly in complex, disturbance-prone environments. |
11 pages, 7 figures |
| GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning | 2025-12-02 | ShowWith the rapid development of Large Vision Language Models, the focus of Graphical User Interface (GUI) agent tasks shifts from single-screen tasks to complex screen navigation challenges. However, real-world GUI environments, such as PC software and mobile Apps, are often complex and proprietary, making it difficult to obtain the comprehensive environment information needed for agent training and evaluation. This limitation hinders systematic investigation and benchmarking of agent navigation capabilities. To address this limitation, we introduce GUI Exploration Lab, a simulation environment engine for GUI agent navigation research that enables flexible definition and composition of screens, icons, and navigation graphs, while providing full access to environment information for comprehensive agent training and evaluation. Through extensive experiments, we find that supervised fine-tuning enables effective memorization of fundamental knowledge, serving as a crucial foundation for subsequent training. Building on this, single-turn reinforcement learning further enhances generalization to unseen scenarios. Finally, multi-turn reinforcement learning encourages the development of exploration strategies through interactive trial and error, leading to further improvements in screen navigation performance. We validate our methods on both static and interactive benchmarks, demonstrating that our findings generalize effectively to real-world scenarios. These findings demonstrate the advantages of reinforcement learning approaches in GUI navigation and offer practical guidance for building more capable and generalizable GUI agents. |
26 pages |
| NavForesee: A Unified Vision-Language World Model for Hierarchical Planning and Dual-Horizon Navigation Prediction | 2025-12-01 | ShowEmbodied navigation for long-horizon tasks, guided by complex natural language instructions, remains a formidable challenge in artificial intelligence. Existing agents often struggle with robust long-term planning about unseen environments, leading to high failure rates. To address these limitations, we introduce NavForesee, a novel Vision-Language Model (VLM) that unifies high-level language planning and predictive world model imagination within a single, unified framework. Our approach empowers a single VLM to concurrently perform planning and predictive foresight. Conditioned on the full instruction and historical observations, the model is trained to understand the navigation instructions by decomposing the task, tracking its progress, and formulating the subsequent sub-goal. Simultaneously, it functions as a generative world model, providing crucial foresight by predicting short-term environmental dynamics and long-term navigation milestones. The VLM's structured plan guides its targeted prediction, while the imagined future provides rich context to inform the navigation actions, creating a powerful internal feedback loop of perception-planning/prediction-action. We demonstrate through extensive experiments on the R2R-CE and RxR-CE benchmark that NavForesee achieves highly competitive performance in complex scenarios. Our work highlights the immense potential of fusing explicit language planning with implicit spatiotemporal prediction, paving the way for more intelligent and capable embodied agents. |
|
| FOM-Nav: Frontier-Object Maps for Object Goal Navigation | 2025-11-30 | ShowThis paper addresses the Object Goal Navigation problem, where a robot must efficiently find a target object in an unknown environment. Existing implicit memory-based methods struggle with long-term memory retention and planning, while explicit map-based approaches lack rich semantic information. To address these challenges, we propose FOM-Nav, a modular framework that enhances exploration efficiency through Frontier-Object Maps and vision-language models. Our Frontier-Object Maps are built online and jointly encode spatial frontiers and fine-grained object information. Using this representation, a vision-language model performs multimodal scene understanding and high-level goal prediction, which is executed by a low-level planner for efficient trajectory generation. To train FOM-Nav, we automatically construct large-scale navigation datasets from real-world scanned environments. Extensive experiments validate the effectiveness of our model design and constructed dataset. FOM-Nav achieves state-of-the-art performance on the MP3D and HM3D benchmarks, particularly in navigation efficiency metric SPL, and yields promising results on a real robot. |
Proje...Project page: https://www.di.ens.fr/willow/research/fom-nav/ |
| Cross Modal Fine-Grained Alignment via Granularity-Aware and Region-Uncertain Modeling | 2025-11-29 | ShowFine-grained image-text alignment is a pivotal challenge in multimodal learning, underpinning key applications such as visual question answering, image captioning, and vision-language navigation. Unlike global alignment, fine-grained alignment requires precise correspondence between localized visual regions and textual tokens, often hindered by noisy attention mechanisms and oversimplified modeling of cross-modal relationships. In this work, we identify two fundamental limitations of existing approaches: the lack of robust intra-modal mechanisms to assess the significance of visual and textual tokens, leading to poor generalization in complex scenes; and the absence of fine-grained uncertainty modeling, which fails to capture the one-to-many and many-to-one nature of region-word correspondences. To address these issues, we propose a unified approach that incorporates significance-aware and granularity-aware modeling and region-level uncertainty modeling. Our method leverages modality-specific biases to identify salient features without relying on brittle cross-modal attention, and represents region features as a mixture of Gaussian distributions to capture fine-grained uncertainty. Extensive experiments on Flickr30K and MS-COCO demonstrate that our approach achieves state-of-the-art performance across various backbone architectures, significantly enhancing the robustness and interpretability of fine-grained image-text alignment. |
10 pa...10 pages, 6 figures, accepted by AAAI 2026 |
| MonoDream: Monocular Vision-Language Navigation with Panoramic Dreaming | 2025-11-27 | ShowVision-Language Navigation (VLN) tasks often leverage panoramic RGB and depth inputs to provide rich spatial cues for action planning, but these sensors can be costly or less accessible in real-world deployments. Recent approaches based on Vision-Language Action (VLA) models achieve strong results with monocular input, yet they still lag behind methods using panoramic RGB-D information. We present MonoDream, a lightweight VLA framework that enables monocular agents to learn a Unified Navigation Representation (UNR). This shared feature representation jointly aligns navigation-relevant visual semantics (e.g., global layout, depth, and future cues) and language-grounded action intent, enabling more reliable action prediction. MonoDream further introduces Latent Panoramic Dreaming (LPD) tasks to supervise the UNR, which train the model to predict latent features of panoramic RGB and depth observations at both current and future steps based on only monocular input. Experiments on multiple VLN benchmarks show that MonoDream consistently improves monocular navigation performance and significantly narrows the gap with panoramic-based agents. |
|
| Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis | 2025-11-27 | ShowFor autonomous vehicles, safe navigation in complex environments depends on handling a broad range of diverse and rare driving scenarios. Simulation- and scenario-based testing have emerged as key approaches to development and validation of autonomous driving systems. Traditional scenario generation relies on rule-based systems, knowledge-driven models, and data-driven synthesis, often producing limited diversity and unrealistic safety-critical cases. With the emergence of foundation models, which represent a new generation of pre-trained, general-purpose AI models, developers can process heterogeneous inputs (e.g., natural language, sensor data, HD maps, and control actions), enabling the synthesis and interpretation of complex driving scenarios. In this paper, we conduct a survey about the application of foundation models for scenario generation and scenario analysis in autonomous driving (as of May 2025). Our survey presents a unified taxonomy that includes large language models, vision-language models, multimodal large language models, diffusion models, and world models for the generation and analysis of autonomous driving scenarios. In addition, we review the methodologies, open-source datasets, simulation platforms, and benchmark challenges, and we examine the evaluation metrics tailored explicitly to scenario generation and analysis. Finally, the survey concludes by highlighting the open challenges and research questions, and outlining promising future research directions. All reviewed papers are listed in a continuously maintained repository, which contains supplementary materials and is available at https://github.com/TUM-AVS/FM-for-Scenario-Generation-Analysis. |
Revis...Revised manuscript with separate evaluation metrics table |
| MedEyes: Learning Dynamic Visual Focus for Medical Progressive Diagnosis | 2025-11-27 | ShowAccurate medical diagnosis often involves progressive visual focusing and iterative reasoning, characteristics commonly observed in clinical workflows. While recent vision-language models demonstrate promising chain-of-thought (CoT) reasoning capabilities via reinforcement learning with verifiable rewards (RLVR), their purely on-policy learning paradigm tends to reinforce superficially coherent but clinically inaccurate reasoning paths. We propose MedEyes, a novel reinforcement learning framework that dynamically models clinician-style diagnostic reasoning by progressively attending to and interpreting relevant medical image regions. By incorporating off-policy expert guidance, MedEyes converts expert visual search trajectories into structured external behavioral signals, guiding the model toward clinically aligned visual reasoning. We design the Gaze-guided Reasoning Navigator (GRN) to emulate the diagnostic process through a dual-mode exploration strategy, scanning for systematic abnormality localization and drilling for detailed regional analysis. To balance expert imitation and autonomous discovery, we introduce the Confidence Value Sampler (CVS), which employs nucleus sampling and adaptive termination to create diverse yet credible exploration paths. Finally, the dual-stream GRPO optimization framework decouples on-policy and off-policy learning signals, mitigating reward assimilation and entropy collapse. Experiments demonstrate that MedEyes achieves an average performance improvement of +8.5% across multiple medical VQA benchmarks, validating MedEyes's potential in building interpretable medical AI systems. |
This ...This paper has been accepted by AAAI 2026 |
| Hibikino-Musashi@Home 2025 Team Description Paper | 2025-11-25 | ShowThis paper provides an overview of the techniques employed by Hibikino-Musashi@Home, which intends to participate in the domestic standard platform league. The team developed a dataset generator for training a robot vision system and an open-source development environment running on a Human Support Robot simulator. The large-language-model-powered task planner selects appropriate primitive skills to perform the task requested by the user. Moreover, the team has focused on research involving brain-inspired memory models for adaptation to individual home environments. This approach aims to provide intuitive and personalized assistance. Additionally, the team contributed to the reusability of the navigation system developed by Pumas in RoboCup2024. The team aimed to design a home service robot to assist humans in their homes and continuously attend competitions to evaluate and improve the developed system. |
|
| FSR-VLN: Fast and Slow Reasoning for Vision-Language Navigation with Hierarchical Multi-modal Scene Graph | 2025-11-25 | ShowVisual-Language Navigation (VLN) is a fundamental challenge in robotic systems, with broad applications for the deployment of embodied agents in real-world environments. Despite recent advances, existing approaches are limited in long-range spatial reasoning, often exhibiting low success rates and high inference latency, particularly in long-range navigation tasks. To address these limitations, we propose FSR-VLN, a vision-language navigation system that combines a Hierarchical Multi-modal Scene Graph (HMSG) with Fast-to-Slow Navigation Reasoning (FSR). The HMSG provides a multi-modal map representation supporting progressive retrieval, from coarse room-level localization to fine-grained goal view and object identification. Building on HMSG, FSR first performs fast matching to efficiently select candidate rooms, views, and objects, then applies VLM-driven refinement for final goal selection. We evaluated FSR-VLN across four comprehensive indoor datasets collected by humanoid robots, utilizing 87 instructions that encompass a diverse range of object categories. FSR-VLN achieves state-of-the-art (SOTA) performance in all datasets, measured by the retrieval success rate (RSR), while reducing the response time by 82% compared to VLM-based methods on tour videos by activating slow reasoning only when fast intuition fails. Furthermore, we integrate FSR-VLN with speech interaction, planning, and control modules on a Unitree-G1 humanoid robot, enabling natural language interaction and real-time navigation. |
Demo ...Demo video are available at https://horizonrobotics.github.io/robot_lab/fsr-vln/ |
| DeeAD: Dynamic Early Exit of Vision-Language Action for Efficient Autonomous Driving | 2025-11-25 | ShowVision-Language Action (VLA) models unify perception, reasoning, and trajectory generation for autonomous driving, but suffer from significant inference latency due to deep transformer stacks. We present DeeAD, a training-free, action-guided early-exit framework that accelerates VLA planning by evaluating the physical feasibility of intermediate trajectories. Instead of relying on confidence scores, DeeAD terminates inference when predicted trajectories align with lightweight planning priors (e.g., Navigation or Low-precision Planning) within a tolerable deviation (<2m). To improve efficiency, we introduce a multi-hop controller that adaptively skips redundant layers based on the change rate of scores. DeeAD integrates into existing VLA models, such as ORION, without requiring retraining. Experiments on the Bench2Drive benchmark demonstrate up to 28% transformer-layer sparsity and 29% latency reduction, while preserving planning quality and safety. |
|
| Vision Language Models Can Parse Floor Plan Maps | 2025-11-24 | ShowVision language models (VLMs) can simultaneously reason about images and texts to tackle many tasks, from visual question answering to image captioning. This paper focuses on map parsing, a novel task that is unexplored within the VLM context and particularly useful to mobile robots. Map parsing requires understanding not only the labels but also the geometric configurations of a map, i.e., what areas are like and how they are connected. To evaluate the performance of VLMs on map parsing, we prompt VLMs with floor plan maps to generate task plans for complex indoor navigation. Our results demonstrate the remarkable capability of VLMs in map parsing, with a success rate of 0.96 in tasks requiring a sequence of nine navigation actions, e.g., approaching and going through doors. Other than intuitive observations, e.g., VLMs do better in smaller maps and simpler navigation tasks, there was a very interesting observation that its performance drops in large open areas. We provide practical suggestions to address such challenges as validated by our experimental results. Webpage: https://sites.google.com/view/vlm-floorplan/ |
|
| Prune-Then-Plan: Step-Level Calibration for Stable Frontier Exploration in Embodied Question Answering | 2025-11-24 | ShowLarge vision-language models (VLMs) have improved embodied question answering (EQA) agents by providing strong semantic priors for open-vocabulary reasoning. However, when used directly for step-level exploration, VLMs often exhibit frontier oscillations, unstable back-and-forth movements caused by overconfidence and miscalibration, leading to inefficient navigation and degraded answer quality. We propose Prune-Then-Plan, a simple and effective framework that stabilizes exploration through step-level calibration. Instead of trusting raw VLM scores, our method prunes implausible frontier choices using a Holm-Bonferroni inspired pruning procedure and then delegates final decisions to a coverage-based planner. This separation converts overconfident predictions into conservative, interpretable actions by relying on human-level judgments to calibrate the step-level behavior of VLMs. Integrated into the 3D-Mem EQA framework, our approach achieves relative improvements of up to 49% and 33% in visually grounded SPL and LLM-Match metrics respectively over baselines. Overall, our method achieves better scene coverage under equal exploration budgets on both OpenEQA and EXPRESS-Bench datasets. |
webpa...webpage: https://noahfrahm.github.io/Prune-Then-Plan-project-page/ |
| UNeMo: Collaborative Visual-Language Reasoning and Navigation via a Multimodal World Model | 2025-11-24 | ShowVision-and-Language Navigation (VLN) requires agents to autonomously navigate complex environments via visual images and natural language instruction--remains highly challenging. Recent research on enhancing language-guided navigation reasoning using pre-trained large language models (LLMs) has shown promising prospects. However, the reasoning of such methods is limited to the linguistic modality, lacking visual reasoning capabilities. Moreover, existing reasoning modules are optimized separately from navigation policies, leading to incompatibility and potential conflicts in optimization objectives. To tackle these challenges, we introduce UNeMo, a novel framework designed for the collaborative optimization of visual state reasoning and navigational decision-making. It introduces a Multimodal World Model (MWM) that takes visual features, language instructions, and navigational actions as inputs to jointly predict subsequent visual states, enabling cross-modal reasoning. Via a Hierarchical Prediction-Feedback (HPN) mechanism, MWM collaborates with navigation policies: the first layer generates actions using current vision-and-language features; MWM then infers post-action visual states to guide the second layer's fine-grained decisions. This forms a dynamic bidirectional promotion mechanism where MWM reasoning optimizes navigation policies, while policy decisions feedback to improve MWM's reasoning accuracy. Experiments on R2R and REVERIE datasets show UNeMo outperforms state-of-the-art methods by 2.1% and 0.7% in navigation accuracy for unseen scenes, validating its effectiveness. |
|
| Boundary on the Table: Efficient Black-Box Decision-Based Attacks for Structured Data | 2025-11-23 | ShowAdversarial robustness in structured data remains an underexplored frontier compared to vision and language domains. In this work, we introduce a novel black-box, decision-based adversarial attack tailored for tabular data. Our approach combines gradient-free direction estimation with an iterative boundary search, enabling efficient navigation of discrete and continuous feature spaces under minimal oracle access. Extensive experiments demonstrate that our method successfully compromises nearly the entire test set across diverse models, ranging from classical machine learning classifiers to large language model (LLM)-based pipelines. Remarkably, the attack achieves success rates consistently above 90%, while requiring only a small number of queries per instance. These results highlight the critical vulnerability of tabular models to adversarial perturbations, underscoring the urgent need for stronger defenses in real-world decision-making systems. |
Paper revision |
| AVERY: Adaptive VLM Split Computing through Embodied Self-Awareness for Efficient Disaster Response Systems | 2025-11-22 | ShowUnmanned Aerial Vehicles (UAVs) in disaster response require complex, queryable intelligence that on-board CNNs cannot provide. While Vision-Language Models (VLMs) offer this semantic reasoning, their high resource demands make on-device deployment infeasible, and naive cloud offloading fails under the low-bandwidth networks common in disaster zones. We present AVERY, a framework that enables VLM deployment through adaptive split computing. We advance the split computing paradigm beyond traditional depth-wise partitioning by introducing a functional, cognitive-inspired dual-stream split that separates the VLM into a high-frequency, low-resolution "context stream" for real-time awareness and a low-frequency, high-fidelity "insight stream" for deep analysis. A lightweight, self-aware on-board controller manages this architecture, monitoring network conditions and operator intent to dynamically select from pre-trained compression models, navigating the fundamental accuracy-throughput trade-off. Evaluated using the VLM LISA-7B across an edge-cloud scenario under fluctuating network conditions, AVERY consistently outperforms static configurations, achieving 11.2% higher accuracy than raw image compression and 93.98% lower energy consumption compared to full-edge execution, thereby enhancing mission efficiency and enabling real-time, queryable intelligence on resource-constrained platforms in dynamic environments. |
8 pag...8 pages, 5 figures. Paper is currently under review. Authors' version posted for personal use and not for redistribution |
| EchoVLA: Robotic Vision-Language-Action Model with Synergistic Declarative Memory for Mobile Manipulation | 2025-11-22 | ShowRecent progress in Vision-Language-Action (VLA) models has enabled embodied agents to interpret multimodal instructions and perform complex tasks. However, existing VLAs are mostly confined to short-horizon, table-top manipulation, lacking the memory and reasoning capability required for long-horizon mobile manipulation, where agents must coordinate navigation and manipulation under changing spatial contexts. In this work, we present EchoVLA, a memory-aware VLA model for long-horizon mobile manipulation. EchoVLA incorporates a synergistic declarative memory inspired by the human brain, consisting of a scene memory that maintains a collection of spatial-semantic maps and an episodic memory that stores task-level experiences with multimodal contextual features. During both training and inference, the two memories are individually stored, updated, and retrieved based on current observations, task history, and instructions, and their retrieved representations are fused via coarse- and fine-grained attention to guide mobile-arm diffusion policies. To support large-scale training and evaluation, we further introduce MoMani, an automated benchmark that generates expert-level long-horizon trajectories through multimodal large language model (MLLM)-guided planning and feedback-driven refinement, supplemented with real-robot demonstrations. Experiments in simulated and real-world settings show that EchoVLA improves long-horizon performance, reaching 0.52 SR on manipulation/navigation and 0.31 on mobile manipulation, exceeding |
|
| IndustryNav: Exploring Spatial Reasoning of Embodied Agents in Dynamic Industrial Navigation | 2025-11-21 | ShowWhile Visual Large Language Models (VLLMs) show great promise as embodied agents, they continue to face substantial challenges in spatial reasoning. Existing embodied benchmarks largely focus on passive, static household environments and evaluate only isolated capabilities, failing to capture holistic performance in dynamic, real-world complexity. To fill this gap, we present IndustryNav, the first dynamic industrial navigation benchmark for active spatial reasoning. IndustryNav leverages 12 manually created, high-fidelity Unity warehouse scenarios featuring dynamic objects and human movement. Our evaluation employs a PointGoal navigation pipeline that effectively combines egocentric vision with global odometry to assess holistic local-global planning. Crucially, we introduce the "collision rate" and "warning rate" metrics to measure safety-oriented behaviors and distance estimation. A comprehensive study of nine state-of-the-art VLLMs (including models such as GPT-5-mini, Claude-4.5, and Gemini-2.5) reveals that closed-source models maintain a consistent advantage; however, all agents exhibit notable deficiencies in robust path planning, collision avoidance and active exploration. This highlights a critical need for embodied research to move beyond passive perception and toward tasks that demand stable planning, active exploration, and safe behavior in dynamic, real-world environment. |
|
| Progress-Think: Semantic Progress Reasoning for Vision-Language Navigation | 2025-11-21 | ShowVision-Language Navigation requires agents to act coherently over long horizons by understanding not only local visual context but also how far they have advanced within a multi-step instruction. However, recent Vision-Language-Action models focus on direct action prediction and earlier progress methods predict numeric achievements; both overlook the monotonic co-progression property of the observation and instruction sequences. Building on this insight, Progress-Think introduces semantic progress reasoning, predicting instruction-style progress from visual observations to enable more accurate navigation. To achieve this without expensive annotations, we propose a three-stage framework. In the initial stage, Self-Aligned Progress Pretraining bootstraps a reasoning module via a novel differentiable alignment between visual history and instruction prefixes. Then, Progress-Guided Policy Pretraining injects learned progress states into the navigation context, guiding the policy toward consistent actions. Finally, Progress-Policy Co-Finetuning jointly optimizes both modules with tailored progress-aware reinforcement objectives. Experiments on R2R-CE and RxR-CE show state-of-the-art success and efficiency, demonstrating that semantic progress yields a more consistent representation of navigation advancement. |
|
| GhostEI-Bench: Do Mobile Agents Resilience to Environmental Injection in Dynamic On-Device Environments? | 2025-11-21 | ShowVision-Language Models (VLMs) are increasingly deployed as autonomous agents to navigate mobile graphical user interfaces (GUIs). Operating in dynamic on-device ecosystems, which include notifications, pop-ups, and inter-app interactions, exposes them to a unique and underexplored threat vector: environmental injection. Unlike prompt-based attacks that manipulate textual instructions, environmental injection corrupts an agent's visual perception by inserting adversarial UI elements (for example, deceptive overlays or spoofed notifications) directly into the GUI. This bypasses textual safeguards and can derail execution, causing privacy leakage, financial loss, or irreversible device compromise. To systematically evaluate this threat, we introduce GhostEI-Bench, the first benchmark for assessing mobile agents under environmental injection attacks within dynamic, executable environments. Moving beyond static image-based assessments, GhostEI-Bench injects adversarial events into realistic application workflows inside fully operational Android emulators and evaluates performance across critical risk scenarios. We further propose a judge-LLM protocol that conducts fine-grained failure analysis by reviewing the agent's action trajectory alongside the corresponding screenshot sequence, pinpointing failure in perception, recognition, or reasoning. Comprehensive experiments on state-of-the-art agents reveal pronounced vulnerability to deceptive environmental cues: current models systematically fail to perceive and reason about manipulated UIs. GhostEI-Bench provides a framework for quantifying and mitigating this emerging threat, paving the way toward more robust and secure embodied agents. |
|
| OpenVLN: Open-world Aerial Vision-Language Navigation | 2025-11-21 | ShowVision-language models (VLMs) have been widely-applied in ground-based vision-language navigation (VLN). However, the vast complexity of outdoor aerial environments compounds data acquisition challenges and imposes long-horizon trajectory planning requirements on Unmanned Aerial Vehicles (UAVs), introducing novel complexities for aerial VLN. To address these challenges, we propose a data-efficient Open-world aerial Vision-Language Navigation (i.e., OpenVLN) framework, which could execute language-guided flight with limited data constraints and enhance long-horizon trajectory planning capabilities in complex aerial environments. Specifically, we reconfigure a reinforcement learning framework to optimize the VLM for UAV navigation tasks, which can efficiently fine-tune VLM by using rule-based policies under limited training data. Concurrently, we introduce a long-horizon planner for trajectory synthesis that dynamically generates precise UAV actions via value-based rewards. To the end, we conduct sufficient navigation experiments on the TravelUAV benchmark with dataset scaling across diverse reward settings. Our method demonstrates consistent performance gains of up to 4.34% in Success Rate, 6.19% in Oracle Success Rate, and 4.07% in Success weighted by Path Length over baseline methods, validating its deployment efficacy for long-horizon UAV navigation in complex aerial environments. |
Conte...Content: 8 pages 4 figures, conference paper under review |
| Automatically Detecting Online Deceptive Patterns | 2025-11-20 | ShowDeceptive patterns in digital interfaces manipulate users into making unintended decisions, exploiting cognitive biases and psychological vulnerabilities. These patterns have become ubiquitous on various digital platforms. While efforts to mitigate deceptive patterns have emerged from legal and technical perspectives, a significant gap remains in creating usable and scalable solutions. We introduce our AutoBot framework to address this gap and help web stakeholders navigate and mitigate online deceptive patterns. AutoBot accurately identifies and localizes deceptive patterns from a screenshot of a website without relying on the underlying HTML code. AutoBot employs a two-stage pipeline that leverages the capabilities of specialized vision models to analyze website screenshots, identify interactive elements, and extract textual features. Next, using a large language model, AutoBot understands the context surrounding these elements to determine the presence of deceptive patterns. We also use AutoBot, to create a synthetic dataset to distill knowledge from 'teacher' LLMs to smaller language models. Through extensive evaluation, we demonstrate AutoBot's effectiveness in detecting deceptive patterns on the web, achieving an F1-score of 0.93 when detecting deceptive patterns, underscoring its potential as an essential tool for mitigating online deceptive patterns. We implement AutoBot, across three downstream applications targeting different web stakeholders: (1) a local browser extension providing users with real-time feedback, (2) a Lighthouse audit to inform developers of potential deceptive patterns on their sites, and (3) as a measurement tool designed for researchers and regulators. |
|
| RoboTidy : A 3D Gaussian Splatting Household Tidying Benchmark for Embodied Navigation and Action | 2025-11-19 | ShowHousehold tidying is an important application area, yet current benchmarks neither model user preferences nor support mobility, and they generalize poorly, making it hard to comprehensively assess integrated language-to-action capabilities. To address this, we propose RoboTidy, a unified benchmark for language-guided household tidying that supports Vision-Language-Action (VLA) and Vision-Language-Navigation (VLN) training and evaluation. RoboTidy provides 500 photorealistic 3D Gaussian Splatting (3DGS) household scenes (covering 500 objects and containers) with collisions, formulates tidying as an "Action (Object, Container)" list, and supplies 6.4k high-quality manipulation demonstration trajectories and 1.5k naviagtion trajectories to support both few-shot and large-scale training. We also deploy RoboTidy in the real world for object tidying, establishing an end-to-end benchmark for household tidying. RoboTidy offers a scalable platform and bridges a key gap in embodied AI by enabling holistic and realistic evaluation of language-guided robots. |
|
| Enhancing End-to-End Autonomous Driving with Risk Semantic Distillaion from VLM | 2025-11-18 | ShowThe autonomous driving (AD) system has exhibited remarkable performance in complex driving scenarios. However, generalization is still a key limitation for the current system, which refers to the ability to handle unseen scenarios or unfamiliar sensor configurations.Related works have explored the use of Vision-Language Models (VLMs) to address few-shot or zero-shot tasks. While promising, these methods introduce a new challenge: the emergence of a hybrid AD system, where two distinct systems are used to plan a trajectory, leading to potential inconsistencies. Alternative research directions have explored Vision-Language-Action (VLA) frameworks that generate control actions from VLM directly. However, these end-to-end solutions demonstrate prohibitive computational demands. To overcome these challenges, we introduce Risk Semantic Distillation (RSD), a novel framework that leverages VLMs to enhance the training of End-to-End (E2E) AD backbones. By providing risk attention for key objects, RSD addresses the issue of generalization. Specifically, we introduce RiskHead, a plug-in module that distills causal risk estimates from Vision-Language Models into Bird's-Eye-View (BEV) features, yielding interpretable risk-attention maps.This approach allows BEV features to learn richer and more nuanced risk attention representations, which directly enhance the model's ability to handle spatial boundaries and risky objects.By focusing on risk attention, RSD aligns better with human-like driving behavior, which is essential to navigate in complex and dynamic environments. Our experiments on the Bench2Drive benchmark demonstrate the effectiveness of RSD in managing complex and unpredictable driving conditions. Due to the enhanced BEV representations enabled by RSD, we observed a significant improvement in both perception and planning capabilities. |
|
| Run, Ruminate, and Regulate: A Dual-process Thinking System for Vision-and-Language Navigation | 2025-11-18 | ShowVision-and-Language Navigation (VLN) requires an agent to dynamically explore complex 3D environments following human instructions. Recent research underscores the potential of harnessing large language models (LLMs) for VLN, given their commonsense knowledge and general reasoning capabilities. Despite their strengths, a substantial gap in task completion performance persists between LLM-based approaches and domain experts, as LLMs inherently struggle to comprehend real-world spatial correlations precisely. Additionally, introducing LLMs is accompanied with substantial computational cost and inference latency. To address these issues, we propose a novel dual-process thinking framework dubbed R3, integrating LLMs' generalization capabilities with VLN-specific expertise in a zero-shot manner. The framework comprises three core modules: Runner, Ruminator, and Regulator. The Runner is a lightweight transformer-based expert model that ensures efficient and accurate navigation under regular circumstances. The Ruminator employs a powerful multimodal LLM as the backbone and adopts chain-of-thought (CoT) prompting to elicit structured reasoning. The Regulator monitors the navigation progress and controls the appropriate thinking mode according to three criteria, integrating Runner and Ruminator harmoniously. Experimental results illustrate that R3 significantly outperforms other state-of-the-art methods, exceeding 3.28% and 3.30% in SPL and RGSPL respectively on the REVERIE benchmark. This pronounced enhancement highlights the effectiveness of our method in handling challenging VLN tasks. |
|
| FreeAskWorld: An Interactive and Closed-Loop Simulator for Human-Centric Embodied AI | 2025-11-17 | ShowAs embodied intelligence emerges as a core frontier in artificial intelligence research, simulation platforms must evolve beyond low-level physical interactions to capture complex, human-centered social behaviors. We introduce FreeAskWorld, an interactive simulation framework that integrates large language models (LLMs) for high-level behavior planning and semantically grounded interaction, informed by theories of intention and social cognition. Our framework supports scalable, realistic human-agent simulations and includes a modular data generation pipeline tailored for diverse embodied tasks.To validate the framework, we extend the classic Vision-and-Language Navigation (VLN) task into a interaction enriched Direction Inquiry setting, wherein agents can actively seek and interpret navigational guidance. We present and publicly release FreeAskWorld, a large-scale benchmark dataset comprising reconstructed environments, six diverse task types, 16 core object categories, 63,429 annotated sample frames, and more than 17 hours of interaction data to support training and evaluation of embodied AI systems. We benchmark VLN models, and human participants under both open-loop and closed-loop settings. Experimental results demonstrate that models fine-tuned on FreeAskWorld outperform their original counterparts, achieving enhanced semantic understanding and interaction competency. These findings underscore the efficacy of socially grounded simulation frameworks in advancing embodied AI systems toward sophisticated high-level planning and more naturalistic human-agent interaction. Importantly, our work underscores that interaction itself serves as an additional information modality. |
9 pages, 4 figures |
| Is your VLM Sky-Ready? A Comprehensive Spatial Intelligence Benchmark for UAV Navigation | 2025-11-17 | ShowVision-Language Models (VLMs), leveraging their powerful visual perception and reasoning capabilities, have been widely applied in Unmanned Aerial Vehicle (UAV) tasks. However, the spatial intelligence capabilities of existing VLMs in UAV scenarios remain largely unexplored, raising concerns about their effectiveness in navigating and interpreting dynamic environments. To bridge this gap, we introduce SpatialSky-Bench, a comprehensive benchmark specifically designed to evaluate the spatial intelligence capabilities of VLMs in UAV navigation. Our benchmark comprises two categories-Environmental Perception and Scene Understanding-divided into 13 subcategories, including bounding boxes, color, distance, height, and landing safety analysis, among others. Extensive evaluations of various mainstream open-source and closed-source VLMs reveal unsatisfactory performance in complex UAV navigation scenarios, highlighting significant gaps in their spatial capabilities. To address this challenge, we developed the SpatialSky-Dataset, a comprehensive dataset containing 1M samples with diverse annotations across various scenarios. Leveraging this dataset, we introduce Sky-VLM, a specialized VLM designed for UAV spatial reasoning across multiple granularities and contexts. Extensive experimental results demonstrate that Sky-VLM achieves state-of-the-art performance across all benchmark tasks, paving the way for the development of VLMs suitable for UAV scenarios. The source code is available at https://github.com/linglingxiansen/SpatialSKy. |
|
| Shedding Light on VLN Robustness: A Black-box Framework for Indoor Lighting-based Adversarial Attack | 2025-11-17 | ShowVision-and-Language Navigation (VLN) agents have made remarkable progress, but their robustness remains insufficiently studied. Existing adversarial evaluations often rely on perturbations that manifest as unusual textures rarely encountered in everyday indoor environments. Errors under such contrived conditions have limited practical relevance, as real-world agents are unlikely to encounter such artificial patterns. In this work, we focus on indoor lighting, an intrinsic yet largely overlooked scene attribute that strongly influences navigation. We propose Indoor Lighting-based Adversarial Attack (ILA), a black-box framework that manipulates global illumination to disrupt VLN agents. Motivated by typical household lighting usage, we design two attack modes: Static Indoor Lighting-based Attack (SILA), where the lighting intensity remains constant throughout an episode, and Dynamic Indoor Lighting-based Attack (DILA), where lights are switched on or off at critical moments to induce abrupt illumination changes. We evaluate ILA on two state-of-the-art VLN models across three navigation tasks. Results show that ILA significantly increases failure rates while reducing trajectory efficiency, revealing previously unrecognized vulnerabilities of VLN agents to realistic indoor lighting variations. |
|
| BridgeEQA: Virtual Embodied Agents for Real Bridge Inspections | 2025-11-16 | ShowDeploying embodied agents that can answer questions about their surroundings in realistic real-world settings remains difficult, partly due to the scarcity of benchmarks that faithfully capture practical operating conditions. We propose infrastructure inspection as a compelling domain for open-vocabulary Embodied Question Answering (EQA): it naturally demands multi-scale reasoning, long-range spatial understanding, and complex semantic relationships, while offering unique evaluation advantages via standardized National Bridge Inventory (NBI) condition ratings (0-9), professional inspection reports, and egocentric imagery. We introduce BridgeEQA, a benchmark of 2,200 open-vocabulary question-answer pairs (in the style of OpenEQA) grounded in professional inspection reports across 200 real-world bridge scenes with 47.93 images on average per scene. Questions require synthesizing visual evidence across multiple images and aligning responses with NBI condition ratings. We further propose a new EQA metric Image Citation Relevance to evaluate the ability of a model to cite relevant images. Evaluations of state-of-the-art vision-language models reveal substantial performance gaps under episodic memory EQA settings. To address this, we propose Embodied Memory Visual Reasoning (EMVR), which formulates inspection as sequential navigation over an image-based scene graph: images are nodes, and an agent takes actions to traverse views, compare evidence, and reason within a Markov decision process. EMVR shows strong performance over the baselines. We publicly release both the dataset and code. |
|
| RoboAfford++: A Generative AI-Enhanced Dataset for Multimodal Affordance Learning in Robotic Manipulation and Navigation | 2025-11-16 | ShowRobotic manipulation and navigation are fundamental capabilities of embodied intelligence, enabling effective robot interactions with the physical world. Achieving these capabilities requires a cohesive understanding of the environment, including object recognition to localize target objects, object affordances to identify potential interaction areas and spatial affordances to discern optimal areas for both object placement and robot movement. While Vision-Language Models (VLMs) excel at high-level task planning and scene understanding, they often struggle to infer actionable positions for physical interaction, such as functional grasping points and permissible placement regions. This limitation stems from the lack of fine-grained annotations for object and spatial affordances in their training datasets. To tackle this challenge, we introduce RoboAfford++, a generative AI-enhanced dataset for multimodal affordance learning for both robotic manipulation and navigation. Our dataset comprises 869,987 images paired with 2.0 million question answering (QA) annotations, covering three critical tasks: object affordance recognition to identify target objects based on attributes and spatial relationships, object affordance prediction to pinpoint functional parts for manipulation, and spatial affordance localization to identify free space for object placement and robot navigation. Complementing this dataset, we propose RoboAfford-Eval, a comprehensive benchmark for assessing affordance-aware prediction in real-world scenarios, featuring 338 meticulously annotated samples across the same three tasks. Extensive experimental results reveal the deficiencies of existing VLMs in affordance learning, while fine-tuning on the RoboAfford++ dataset significantly enhances their ability to reason about object and spatial affordances, validating the dataset's effectiveness. |
|
| Imagine in Space: Exploring the Frontier of Spatial Intelligence and Reasoning Efficiency in Vision Language Models | 2025-11-16 | ShowLarge language models (LLMs) and vision language models (VLMs), such as DeepSeek R1,OpenAI o3, and Gemini 2.5 Pro, have demonstrated remarkable reasoning capabilities across logical inference, problem solving, and decision making. However, spatial reasoning:a fundamental component of human cognition that includes mental rotation, navigation, and spatial relationship comprehension remains a significant challenge for current advanced VLMs. We hypothesize that imagination, the internal simulation of spatial states, is the dominant reasoning mechanism within a spatial world model. To test this hypothesis and systematically probe current VLM spatial reasoning mechanisms, we introduce SpatiaLite, a fully synthetic benchmark that jointly measures spatial reasoning accuracy and reasoning efficiency. Comprehensive experiments reveal three key findings. First, advanced VLMs predominantly rely on linguistic representations for reasoning and imagination, resulting in significant deficiencies on visual centric tasks that demand perceptual spatial relations and 3D geometry transformations such as mental rotation or projection prediction. Second, advanced VLMs exhibit severe inefficiency in their current spatial reasoning mechanisms, with token usage growing rapidly as transformation complexity increases. Third, we propose an Imagery Driven Framework (IDF) for data synthesis and training, which can implicitly construct an internal world model that is critical for spatial reasoning in VLMs. Building on SpatiaLite, this work delineates the spatial reasoning limits and patterns of advanced VLMs, identifies key shortcomings, and informs future advances |
10 pa...10 pages,a detail and effective benchmark for spatial reasoning |
| RAC3: Retrieval-Augmented Corner Case Comprehension for Autonomous Driving with Vision-Language Models | 2025-11-15 | ShowUnderstanding and addressing corner cases is essential for ensuring the safety and reliability of autonomous driving systems. Vision-language models (VLMs) play a crucial role in enhancing scenario comprehension, yet they face significant challenges, such as hallucination and insufficient real-world grounding, which compromise their performance in critical driving scenarios. In this work, RAC3, a novel framework designed to enhance the performance of VLMs in corner case comprehension, is proposed. RAC3 integrates a frequency-spatial fusion (FSF) image encoder, a cross-modal alignment training method for embedding models with hard and semi-hard negative mining, and a fast querying and retrieval pipeline based on K-Means clustering and hierarchical navigable small world (HNSW) indexing. A multimodal chain-of-thought (CoT) prompting strategy to guide analogical reasoning and reduce hallucinations during inference is introduced. Moreover, an update mechanism is integrated into RAC3 to ensure continual learning within the framework. Extensive experiments on the CODA and nuScenes datasets demonstrate that RAC3 significantly improves corner case comprehension across multiple downstream tasks. Compared to prior state-of-the-art methods, RAC3 achieves the highest final score of 74.46 on the CODA-LM benchmark and shows consistent performance gains when integrated with end-to-end frameworks like DriveLM. These results demonstrate the effectiveness of retrieval-augmented strategies and cross-modal alignment for safer and more interpretable autonomous driving. |
Accep...Accepted by IEEE Transactions on Multimedia |
| DocLens : A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding | 2025-11-14 | ShowComprehending long visual documents, where information is distributed across extensive pages of text and visual elements, is a critical but challenging task for modern Vision-Language Models (VLMs). Existing approaches falter on a fundamental challenge: evidence localization. They struggle to retrieve relevant pages and overlook fine-grained details within visual elements, leading to limited performance and model hallucination. To address this, we propose DocLens, a tool-augmented multi-agent framework that effectively ``zooms in'' on evidence like a lens. It first navigates from the full document to specific visual elements on relevant pages, then employs a sampling-adjudication mechanism to generate a single, reliable answer. Paired with Gemini-2.5-Pro, DocLens achieves state-of-the-art performance on MMLongBench-Doc and FinRAGBench-V, surpassing even human experts. The framework's superiority is particularly evident on vision-centric and unanswerable queries, demonstrating the power of its enhanced localization capabilities. |
|
| Refine and Align: Confidence Calibration through Multi-Agent Interaction in VQA | 2025-11-14 | ShowIn the context of Visual Question Answering (VQA) and Agentic AI, calibration refers to how closely an AI system's confidence in its answers reflects their actual correctness. This aspect becomes especially important when such systems operate autonomously and must make decisions under visual uncertainty. While modern VQA systems, powered by advanced vision-language models (VLMs), are increasingly used in high-stakes domains like medical diagnostics and autonomous navigation due to their improved accuracy, the reliability of their confidence estimates remains under-examined. Particularly, these systems often produce overconfident responses. To address this, we introduce AlignVQA, a debate-based multi-agent framework, in which diverse specialized VLM -- each following distinct prompting strategies -- generate candidate answers and then engage in two-stage interaction: generalist agents critique, refine and aggregate these proposals. This debate process yields confidence estimates that more accurately reflect the model's true predictive performance. We find that more calibrated specialized agents produce better aligned confidences. Furthermore, we introduce a novel differentiable calibration-aware loss function called aligncal designed to fine-tune the specialized agents by minimizing an upper bound on the calibration error. This objective explicitly improves the fidelity of each agent's confidence estimates. Empirical results across multiple benchmark VQA datasets substantiate the efficacy of our approach, demonstrating substantial reductions in calibration discrepancies. Furthermore, we propose a novel differentiable calibration-aware loss to fine-tune the specialized agents and improve the quality of their individual confidence estimates based on minimising upper bound calibration error. |
17 pa...17 pages, 6 figures, 5 tables. Accepted to Special Track on AI Alignment, AAAI 2026. Project Page- https://refine-align.github.io/ |
| VISTAv2: World Imagination for Indoor Vision-and-Language Navigation | 2025-11-14 | ShowVision-and-Language Navigation (VLN) requires agents to follow language instructions while acting in continuous real-world spaces. Prior image imagination based VLN work shows benefits for discrete panoramas but lacks online, action-conditioned predictions and does not produce explicit planning values; moreover, many methods replace the planner with long-horizon objectives that are brittle and slow. To bridge this gap, we propose VISTAv2, a generative world model that rolls out egocentric future views conditioned on past observations, candidate action sequences, and instructions, and projects them into an online value map for planning. Unlike prior approaches, VISTAv2 does not replace the planner. The online value map is fused at score level with the base objective, providing reachability and risk-aware guidance. Concretely, we employ an action-aware Conditional Diffusion Transformer video predictor to synthesize short-horizon futures, align them with the natural language instruction via a vision-language scorer, and fuse multiple rollouts in a differentiable imagination-to-value head to output an imagined egocentric value map. For efficiency, rollouts occur in VAE latent space with a distilled sampler and sparse decoding, enabling inference on a single consumer GPU. Evaluated on MP3D and RoboTHOR, VISTAv2 improves over strong baselines, and ablations show that action-conditioned imagination, instruction-guided value fusion, and the online value-map planner are all critical, suggesting that VISTAv2 offers a practical and interpretable route to robust VLN. |
11 pages, 5 figures |
| Towards Blind and Low-Vision Accessibility of Lightweight VLMs and Custom LLM-Evals | 2025-11-13 | ShowLarge Vision-Language Models (VLMs) excel at understanding and generating video descriptions but their high memory, computation, and deployment demands hinder practical use particularly for blind and low-vision (BLV) users who depend on detailed, context-aware descriptions. To study the effect of model size on accessibility-focused description quality, we evaluate SmolVLM2 variants with 500M and 2.2B parameters across two diverse datasets: AVCaps (outdoor), and Charades (indoor). In this work, we introduce two novel evaluation frameworks specifically designed for BLV accessibility assessment: the Multi-Context BLV Framework evaluating spatial orientation, social interaction, action events, and ambience contexts; and the Navigational Assistance Framework focusing on mobility-critical information. Additionally, we conduct a systematic evaluation of four different prompt design strategies and deploy both models on a smartphone, evaluating FP32 and INT8 precision variants to assess real-world performance constraints on resource-limited mobile devices. |
8 pages |
| Agent Journey Beyond RGB: Hierarchical Semantic-Spatial Representation Enrichment for Vision-and-Language Navigation | 2025-11-13 | ShowNavigating unseen environments from natural language instructions remains challenging for egocentric agents in Vision-and-Language Navigation (VLN). Humans naturally ground concrete semantic knowledge within spatial layouts during indoor navigation. Although prior work has introduced diverse environment representations to improve reasoning, auxiliary modalities are often naively concatenated with RGB features, which underutilizes each modality's distinct contribution. We propose a hierarchical Semantic Understanding and Spatial Awareness (SUSA) architecture to enable agents to perceive and ground environments at multiple scales. Specifically, the Textual Semantic Understanding (TSU) module supports local action prediction by generating view-level descriptions, capturing fine-grained semantics and narrowing the modality gap between instructions and environments. Complementarily, the Depth Enhanced Spatial Perception (DSP) module incrementally builds a trajectory-level depth exploration map, providing a coarse-grained representation of global spatial layout. Extensive experiments show that the hierarchical representation enrichment of SUSA significantly improves navigation performance over the baseline on discrete VLN benchmarks (REVERIE, R2R, and SOON) and generalizes better to the continuous R2R-CE benchmark. |
AAAI2...AAAI2026, I14 pages, 12 figures, 11 tables |
| From Street to Orbit: Training-Free Cross-View Retrieval via Location Semantics and LLM Guidance | 2025-11-12 | ShowCross-view image retrieval, particularly street-to-satellite matching, is a critical task for applications such as autonomous navigation, urban planning, and localization in GPS-denied environments. However, existing approaches often require supervised training on curated datasets and rely on panoramic or UAV-based images, which limits real-world deployment. In this paper, we present a simple yet effective cross-view image retrieval framework that leverages a pretrained vision encoder and a large language model (LLM), requiring no additional training. Given a monocular street-view image, our method extracts geographic cues through web-based image search and LLM-based location inference, generates a satellite query via geocoding API, and retrieves matching tiles using a pretrained vision encoder (e.g., DINOv2) with PCA-based whitening feature refinement. Despite using no ground-truth supervision or finetuning, our proposed method outperforms prior learning-based approaches on the benchmark dataset under zero-shot settings. Moreover, our pipeline enables automatic construction of semantically aligned street-to-satellite datasets, which is offering a scalable and cost-efficient alternative to manual annotation. All source codes will be made publicly available at https://jeonghomin.github.io/street2orbit.github.io/. |
Accep...Accepted to WACV 2026, 10pages, 4 figures |
| Spatio-Temporal Data Enhanced Vision-Language Model for Traffic Scene Understanding | 2025-11-12 | ShowNowadays, navigation and ride-sharing apps have collected numerous images with spatio-temporal data. A core technology for analyzing such images, associated with spatiotemporal information, is Traffic Scene Understanding (TSU), which aims to provide a comprehensive description of the traffic scene. Unlike traditional spatio-temporal data analysis tasks, the dependence on both spatio-temporal and visual-textual data introduces distinct challenges to TSU task. However, recent research often treats TSU as a common image understanding task, ignoring the spatio-temporal information and overlooking the interrelations between different aspects of the traffic scene. To address these issues, we propose a novel SpatioTemporal Enhanced Model based on CILP (ST-CLIP) for TSU. Our model uses the classic vision-language model, CLIP, as the backbone, and designs a Spatio-temporal Context Aware Multiaspect Prompt (SCAMP) learning method to incorporate spatiotemporal information into TSU. The prompt learning method consists of two components: A dynamic spatio-temporal context representation module that extracts representation vectors of spatio-temporal data for each traffic scene image, and a bi-level ST-aware multi-aspect prompt learning module that integrates the ST-context representation vectors into word embeddings of prompts for the CLIP model. The second module also extracts low-level visual features and image-wise high-level semantic features to exploit interactive relations among different aspects of traffic scenes. To the best of our knowledge, this is the first attempt to integrate spatio-temporal information into visionlanguage models to facilitate TSU task. Experiments on two realworld datasets demonstrate superior performance in the complex scene understanding scenarios with a few-shot learning strategy. |
|
| Think, Remember, Navigate: Zero-Shot Object-Goal Navigation with VLM-Powered Reasoning | 2025-11-12 | ShowWhile Vision-Language Models (VLMs) are set to transform robotic navigation, existing methods often underutilize their reasoning capabilities. To unlock the full potential of VLMs in robotics, we shift their role from passive observers to active strategists in the navigation process. Our framework outsources high-level planning to a VLM, which leverages its contextual understanding to guide a frontier-based exploration agent. This intelligent guidance is achieved through a trio of techniques: structured chain-of-thought prompting that elicits logical, step-by-step reasoning; dynamic inclusion of the agent's recent action history to prevent getting stuck in loops; and a novel capability that enables the VLM to interpret top-down obstacle maps alongside first-person views, thereby enhancing spatial awareness. When tested on challenging benchmarks like HM3D, Gibson, and MP3D, this method produces exceptionally direct and logical trajectories, marking a substantial improvement in navigation efficiency over existing approaches and charting a path toward more capable embodied agents. |
|
| Expand Your SCOPE: Semantic Cognition over Potential-Based Exploration for Embodied Visual Navigation | 2025-11-12 | ShowEmbodied visual navigation remains a challenging task, as agents must explore unknown environments with limited knowledge. Existing zero-shot studies have shown that incorporating memory mechanisms to support goal-directed behavior can improve long-horizon planning performance. However, they overlook visual frontier boundaries, which fundamentally dictate future trajectories and observations, and fall short of inferring the relationship between partial visual observations and navigation goals. In this paper, we propose Semantic Cognition Over Potential-based Exploration (SCOPE), a zero-shot framework that explicitly leverages frontier information to drive potential-based exploration, enabling more informed and goal-relevant decisions. SCOPE estimates exploration potential with a Vision-Language Model and organizes it into a spatio-temporal potential graph, capturing boundary dynamics to support long-horizon planning. In addition, SCOPE incorporates a self-reconsideration mechanism that revisits and refines prior decisions, enhancing reliability and reducing overconfident errors. Experimental results on two diverse embodied navigation tasks show that SCOPE outperforms state-of-the-art baselines by 4.6% in accuracy. Further analysis demonstrates that its core components lead to improved calibration, stronger generalization, and higher decision quality. |
|
| Ariadne: A Controllable Framework for Probing and Extending VLM Reasoning Boundaries | 2025-11-11 | ShowWhile Vision-Language Models (VLMs) post-trained with Reinforcement Learning (RL) show impressive general reasoning, their evaluation is often confined to language-dominant tasks (e.g., math). This raises a critical question: can RL post-training truly extend the inherent capability boundary of a base VLM, particularly for visual-centric spatial tasks where it initially fails? To investigate this, we introduce Ariadne, a framework utilizing synthetic mazes for multi-step spatial reasoning where task difficulty (e.g., path length, turns) is precisely controlled. We leverage this controllable environment to train VLMs using Reinforcement Learning with Verified Rewards (RLVR) in a difficulty-aware curriculum. Surprisingly, post-RLVR training, the VLM achieves over 50% accuracy on a problem set where the base model scored 0%, demonstrating that our approach expands the model's initial capability boundary. To assess real-world viability, we evaluate out-of-distribution (OOD) generalization on practical benchmarks. Despite training only on synthetic maze samples, Ariadne achieves significant zero-shot improvements, averaging 16% on MapBench (e.g., museum navigation) and 24% on ReasonMap (subway transfer tasks). These results confirm that our method not only broadens the model's fundamental limits but also enhances its generalization to real-world spatial reasoning. We acknowledge our study is limited to the post-training phase, given the opaqueness of pre-training data, and hope our research motivates further work on specialized, capability-extending alignment. |
|
| LaF-GRPO: In-Situ Navigation Instruction Generation for the Visually Impaired via GRPO with LLM-as-Follower Reward | 2025-11-11 | ShowNavigation instruction generation for visually impaired (VI) individuals (NIG-VI) is critical yet relatively underexplored. This study focuses on generating precise, in-situ, step-by-step navigation instructions that are practically usable for VI users. Specifically, we propose LaF-GRPO (LLM-as-Follower GRPO), where an LLM simulates VI user responses to navigation instructions, thereby providing feedback rewards to guide the post-training of a Vision-Language Model (VLM). This enhances instruction accuracy and usability while reducing costly real-world data collection needs. To address the scarcity of dedicated benchmarks in this field, we introduce NIG4VI, a 27k-sample open-source dataset to facilitate training and evaluation. It comprises diverse navigation scenarios with accurate spatial coordinates, supporting detailed and open-ended in-situ instruction generation. Experiments on NIG4VI demonstrate the effectiveness of LaF-GRPO through quantitative metrics (e.g., Zero-(LaF-GRPO) boosts BLEU 14%; SFT+(LaF-GRPO) METEOR 0.542 vs. GPT-4o 0.323), and qualitative analysis further confirms that our method yields more intuitive and safer instructions. |
Accepted at AAAI-26 |
| SCoTT: Strategic Chain-of-Thought Tasking for Wireless-Aware Robot Navigation in Digital Twins | 2025-11-11 | ShowPath planning under wireless performance constraints is a complex challenge in robot navigation. However, naively incorporating such constraints into classical planning algorithms often incurs prohibitive search costs. In this paper, we propose SCoTT, a wireless-aware path planning framework that leverages vision-language models (VLMs) to co-optimize average path gains and trajectory length using wireless heatmap images and ray-tracing data from a digital twin (DT). At the core of our framework is Strategic Chain-of-Thought Tasking (SCoTT), a novel prompting paradigm that decomposes the exhaustive search problem into structured subtasks, each solved via chain-of-thought prompting. To establish strong baselines, we compare classical A* and wireless-aware extensions of it, and derive DP-WA*, an optimal, iterative dynamic programming algorithm that incorporates all path gains and distance metrics from the DT, but at significant computational cost. In extensive experiments, we show that SCoTT achieves path gains within 2% of DP-WA* while consistently generating shorter trajectories. Moreover, SCoTT's intermediate outputs can be used to accelerate DP-WA* by reducing its search space, saving up to 62% in execution time. We validate our framework using four VLMs, demonstrating effectiveness across both large and small models, thus making it applicable to a wide range of compact models at low inference cost. We also show the practical viability of our approach by deploying SCoTT as a ROS node within Gazebo simulations. Finally, we discuss data acquisition pipelines, compute requirements, and deployment considerations for VLMs in 6G-enabled DTs, underscoring the potential of natural language interfaces for wireless-aware navigation in real-world applications. |
|
| LLM-GROP: Visually Grounded Robot Task and Motion Planning with Large Language Models | 2025-11-11 | ShowTask planning and motion planning are two of the most important problems in robotics, where task planning methods help robots achieve high-level goals and motion planning methods maintain low-level feasibility. Task and motion planning (TAMP) methods interleave the two processes of task planning and motion planning to ensure goal achievement and motion feasibility. Within the TAMP context, we are concerned with the mobile manipulation (MoMa) of multiple objects, where it is necessary to interleave actions for navigation and manipulation. In particular, we aim to compute where and how each object should be placed given underspecified goals, such as |
|
| Accessibility, Safety, and Accommodation Burden in U.S. Higher Education Syllabi for Blind and Low-Vision Students | 2025-11-10 | ShowCourse syllabi are often the first and sometimes only structured artifact that explains how a class will run: deadlines, grading rules, safety procedures, and how to request disability accommodations. For blind and low-vision (BLV) students who use screen readers, independent access depends on whether the syllabus is machine readable and navigable. We audited publicly posted syllabi and master syllabi from five U.S. institutions spanning an elite private R1 university, large public R1s (including a UC campus), a large community college, and a workforce focused technical college. We coded each document on five dimensions: (1) machine-readability of core logistics, (2) readability of safety critical procedures, (3) accommodation framing (rights based vs. burden based), (4) governance model (instructor-authored vs. centralized "master syllabus"), and (5) presence of proactive universal design language. Across the sample, logistics and many safety expectations are published as selectable text. Accommodation language, however, shifts by institution type: research universities more often use rights based wording (while still requiring advance letters), whereas community/technical colleges emphasize disclosure, documentation, and institutional discretion in master syllabi that replicate across sections. We argue that accessibility is not only a PDF tagging problem but also a question of governance and equity, and we outline implications for HCI, including an "accessible master syllabus" template as a high leverage intervention. |
Prepr...Preprint. LaTeX (acmart, nonacm). 13 pages. Includes 8 tables and 4 figures |
| Visual Hand Gesture Recognition with Deep Learning: A Comprehensive Review of Methods, Datasets, Challenges and Future Research Directions | 2025-11-09 | ShowThe rapid evolution of deep learning (DL) models and the ever-increasing size of available datasets have raised the interest of the research community in the always important field of visual hand gesture recognition (VHGR), and delivered a wide range of applications, such as sign language understanding and human-computer interaction using cameras. Despite the large volume of research works in the field, a structured and complete survey on VHGR is still missing, leaving researchers to navigate through hundreds of papers in order to find the right combination of data, model, and approach for each task. The current survey aims to fill this gap by presenting a comprehensive overview of this computer vision field. With a systematic research methodology that identifies the state-of-the-art works and a structured presentation of the various methods, datasets, and evaluation metrics, this review aims to constitute a useful guideline for researchers, helping them to choose the right strategy for handling a VHGR task. Starting with the methodology used to locate the related literature, the survey identifies and organizes the key VHGR approaches in a taxonomy-based format, and presents the various dimensions that affect the final method choice, such as input modality, task type, and application domain. The state-of-the-art techniques are grouped across three primary VHGR tasks: static gesture recognition, isolated dynamic gestures, and continuous gesture recognition. For each task, the architectural trends and learning strategies are listed. To support the experimental evaluation of future methods in the field, the study reviews commonly used datasets and presents the standard performance metrics. Our survey concludes by identifying the major challenges in VHGR, including both general computer vision issues and domain-specific obstacles, and outlines promising directions for future research. |
|
| Affordance-Guided Coarse-to-Fine Exploration for Base Placement in Open-Vocabulary Mobile Manipulation | 2025-11-09 | ShowIn open-vocabulary mobile manipulation (OVMM), task success often hinges on the selection of an appropriate base placement for the robot. Existing approaches typically navigate to proximity-based regions without considering affordances, resulting in frequent manipulation failures. We propose Affordance-Guided Coarse-to-Fine Exploration, a zero-shot framework for base placement that integrates semantic understanding from vision-language models (VLMs) with geometric feasibility through an iterative optimization process. Our method constructs cross-modal representations, namely Affordance RGB and Obstacle Map+, to align semantics with spatial context. This enables reasoning that extends beyond the egocentric limitations of RGB perception. To ensure interaction is guided by task-relevant affordances, we leverage coarse semantic priors from VLMs to guide the search toward task-relevant regions and refine placements with geometric constraints, thereby reducing the risk of convergence to local optima. Evaluated on five diverse open-vocabulary mobile manipulation tasks, our system achieves an 85% success rate, significantly outperforming classical geometric planners and VLM-based methods. This demonstrates the promise of affordance-aware and multimodal reasoning for generalizable, instruction-conditioned planning in OVMM. |
Accep...Accepted to AAAI 2026 |
| The Dark Side of Rich Rewards: Understanding and Mitigating Noise in VLM Rewards | 2025-11-08 | ShowWhile Vision-Language Models (VLMs) are increasingly used to generate reward signals for training embodied agents to follow instructions, our research reveals that agents guided by VLM rewards often underperform compared to those employing only intrinsic (exploration-driven) rewards, contradicting expectations set by recent work. We hypothesize that false positive rewards -- instances where unintended trajectories are incorrectly rewarded -- are more detrimental than false negatives. Our analysis confirms this hypothesis, revealing that the widely used cosine similarity metric is prone to false positive reward estimates. To address this, we introduce BiMI ({Bi}nary {M}utual {I}nformation), a novel reward function designed to mitigate noise. BiMI significantly enhances learning efficiency across diverse and challenging embodied navigation environments. Our findings offer a nuanced understanding of how different types of reward noise impact agent learning and highlight the importance of addressing multimodal reward signal noise when training embodied agents |
accep...accepted by PRL Workshop Series @ ICAPS 2025. 11 main body pages, 21 appendix pages |
| Search-TTA: A Multimodal Test-Time Adaptation Framework for Visual Search in the Wild | 2025-11-07 | ShowTo perform outdoor visual navigation and search, a robot may leverage satellite imagery to generate visual priors. This can help inform high-level search strategies, even when such images lack sufficient resolution for target recognition. However, many existing informative path planning or search-based approaches either assume no prior information, or use priors without accounting for how they were obtained. Recent work instead utilizes large Vision Language Models (VLMs) for generalizable priors, but their outputs can be inaccurate due to hallucination, leading to inefficient search. To address these challenges, we introduce Search-TTA, a multimodal test-time adaptation framework with a flexible plug-and-play interface compatible with various input modalities (e.g., image, text, sound) and planning methods (e.g., RL-based). First, we pretrain a satellite image encoder to align with CLIP's visual encoder to output probability distributions of target presence used for visual search. Second, our TTA framework dynamically refines CLIP's predictions during search using uncertainty-weighted gradient updates inspired by Spatial Poisson Point Processes. To train and evaluate Search-TTA, we curate AVS-Bench, a visual search dataset based on internet-scale ecological data containing 380k images and taxonomy data. We find that Search-TTA improves planner performance by up to 30.0%, particularly in cases with poor initial CLIP predictions due to domain mismatch and limited training data. It also performs comparably with significantly larger VLMs, and achieves zero-shot generalization via emergent alignment to unseen modalities. Finally, we deploy Search-TTA on a real UAV via hardware-in-the-loop testing, by simulating its operation within a large-scale simulation that provides onboard sensing. |
Accep...Accepted for presentation at CORL 2025. Code, models, and data are available at https://search-tta.github.io/ |
| Toward Engineering AGI: Benchmarking the Engineering Design Capabilities of LLMs | 2025-11-06 | ShowModern engineering, spanning electrical, mechanical, aerospace, civil, and computer disciplines, stands as a cornerstone of human civilization and the foundation of our society. However, engineering design poses a fundamentally different challenge for large language models (LLMs) compared with traditional textbook-style problem solving or factual question answering. Although existing benchmarks have driven progress in areas such as language understanding, code synthesis, and scientific problem solving, real-world engineering design demands the synthesis of domain knowledge, navigation of complex trade-offs, and management of the tedious processes that consume much of practicing engineers' time. Despite these shared challenges across engineering disciplines, no benchmark currently captures the unique demands of engineering design work. In this work, we introduce EngDesign, an Engineering Design benchmark that evaluates LLMs' abilities to perform practical design tasks across nine engineering domains. Unlike existing benchmarks that focus on factual recall or question answering, EngDesign uniquely emphasizes LLMs' ability to synthesize domain knowledge, reason under constraints, and generate functional, objective-oriented engineering designs. Each task in EngDesign represents a real-world engineering design problem, accompanied by a detailed task description specifying design goals, constraints, and performance requirements. EngDesign pioneers a simulation-based evaluation paradigm that moves beyond textbook knowledge to assess genuine engineering design capabilities and shifts evaluation from static answer checking to dynamic, simulation-driven functional verification, marking a crucial step toward realizing the vision of engineering Artificial General Intelligence (AGI). |
To Ap...To Appear in NeurIPS 2025 Datasets & Benchmarks Track |
| A Survey on Improving Human Robot Collaboration through Vision-and-Language Navigation | 2025-11-06 | ShowVision-and-Language Navigation (VLN) is a multi-modal, cooperative task requiring agents to interpret human instructions, navigate 3D environments, and communicate effectively under ambiguity. This paper presents a comprehensive review of recent VLN advancements in robotics and outlines promising directions to improve multi-robot coordination. Despite progress, current models struggle with bidirectional communication, ambiguity resolution, and collaborative decision-making in the multi-agent systems. We review approximately 200 relevant articles to provide an in-depth understanding of the current landscape. Through this survey, we aim to provide a thorough resource that inspires further research at the intersection of VLN and robotics. We advocate that the future VLN systems should support proactive clarification, real-time feedback, and contextual reasoning through advanced natural language understanding (NLU) techniques. Additionally, decentralized decision-making frameworks with dynamic role assignment are essential for scalable, efficient multi-robot collaboration. These innovations can significantly enhance human-robot interaction (HRI) and enable real-world deployment in domains such as healthcare, logistics, and disaster response. |
|
| Team Xiaomi EV-AD VLA: Caption-Guided Retrieval System for Cross-Modal Drone Navigation -- Technical Report for IROS 2025 RoboSense Challenge Track 4 | 2025-11-06 | ShowCross-modal drone navigation remains a challenging task in robotics, requiring efficient retrieval of relevant images from large-scale databases based on natural language descriptions. The RoboSense 2025 Track 4 challenge addresses this challenge, focusing on robust, natural language-guided cross-view image retrieval across multiple platforms (drones, satellites, and ground cameras). Current baseline methods, while effective for initial retrieval, often struggle to achieve fine-grained semantic matching between text queries and visual content, especially in complex aerial scenes. To address this challenge, we propose a two-stage retrieval refinement method: Caption-Guided Retrieval System (CGRS) that enhances the baseline coarse ranking through intelligent reranking. Our method first leverages a baseline model to obtain an initial coarse ranking of the top 20 most relevant images for each query. We then use Vision-Language-Model (VLM) to generate detailed captions for these candidate images, capturing rich semantic descriptions of their visual content. These generated captions are then used in a multimodal similarity computation framework to perform fine-grained reranking of the original text query, effectively building a semantic bridge between the visual content and natural language descriptions. Our approach significantly improves upon the baseline, achieving a consistent 5% improvement across all key metrics (Recall@1, Recall@5, and Recall@10). Our approach win TOP-2 in the challenge, demonstrating the practical value of our semantic refinement strategy in real-world robotic navigation scenarios. |
|
| SENT Map -- Semantically Enhanced Topological Maps with Foundation Models | 2025-11-05 | ShowWe introduce SENT-Map, a semantically enhanced topological map for representing indoor environments, designed to support autonomous navigation and manipulation by leveraging advancements in foundational models (FMs). Through representing the environment in a JSON text format, we enable semantic information to be added and edited in a format that both humans and FMs understand, while grounding the robot to existing nodes during planning to avoid infeasible states during deployment. Our proposed framework employs a two stage approach, first mapping the environment alongside an operator with a Vision-FM, then using the SENT-Map representation alongside a natural-language query within an FM for planning. Our experimental results show that semantic-enhancement enables even small locally-deployable FMs to successfully plan over indoor environments. |
Accep...Accepted at ICRA 2025 Workshop on Foundation Models and Neuro-Symbolic AI for Robotics |
| ROADWork: A Dataset and Benchmark for Learning to Recognize, Observe, Analyze and Drive Through Work Zones | 2025-11-04 | ShowPerceiving and autonomously navigating through work zones is a challenging and underexplored problem. Open datasets for this long-tailed scenario are scarce. We propose the ROADWork dataset to learn to recognize, observe, analyze, and drive through work zones. State-of-the-art foundation models fail when applied to work zones. Fine-tuning models on our dataset significantly improves perception and navigation in work zones. With ROADWork dataset, we discover new work zone images with higher precision (+32.5%) at a much higher rate (12.8$\times$) around the world. Open-vocabulary methods fail too, whereas fine-tuned detectors improve performance (+32.2 AP). Vision-Language Models (VLMs) struggle to describe work zones, but fine-tuning substantially improves performance (+36.7 SPICE). Beyond fine-tuning, we show the value of simple techniques. Video label propagation provides additional gains (+2.6 AP) for instance segmentation. While reading work zone signs, composing a detector and text spotter via crop-scaling improves performance +14.2% 1-NED). Composing work zone detections to provide context further reduces hallucinations (+3.9 SPICE) in VLMs. We predict navigational goals and compute drivable paths from work zone videos. Incorporating road work semantics ensures 53.6% goals have angular error (AE) < 0.5 (+9.9 %) and 75.3% pathways have AE < 0.5 (+8.1 %). |
ICCV ...ICCV 2025 Accepted Paper |
| NaviTrace: Evaluating Embodied Navigation of Vision-Language Models | 2025-11-04 | ShowVision-language models demonstrate unprecedented performance and generalization across a wide range of tasks and scenarios. Integrating these foundation models into robotic navigation systems opens pathways toward building general-purpose robots. Yet, evaluating these models' navigation capabilities remains constrained by costly real-world trials, overly simplified simulations, and limited benchmarks. We introduce NaviTrace, a high-quality Visual Question Answering benchmark where a model receives an instruction and embodiment type (human, legged robot, wheeled robot, bicycle) and must output a 2D navigation trace in image space. Across 1000 scenarios and more than 3000 expert traces, we systematically evaluate eight state-of-the-art VLMs using a newly introduced semantic-aware trace score. This metric combines Dynamic Time Warping distance, goal endpoint error, and embodiment-conditioned penalties derived from per-pixel semantics and correlates with human preferences. Our evaluation reveals consistent gap to human performance caused by poor spatial grounding and goal localization. NaviTrace establishes a scalable and reproducible benchmark for real-world robotic navigation. The benchmark and leaderboard can be found at https://leggedrobotics.github.io/navitrace_webpage/. |
9 pag...9 pages, 6 figures, under review at IEEE conference |
| Unseen from Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigation | 2025-11-04 | ShowData scarcity is a long-standing challenge in the Vision-Language Navigation (VLN) field, which extremely hinders the generalization of agents to unseen environments. Previous works primarily rely on additional simulator data or web-collected images/videos to improve the generalization. However, the simulator environments still face limited diversity, and the web-collected data often requires extensive labor to remove the noise. In this paper, we propose a Rewriting-driven AugMentation (RAM) paradigm for VLN, which directly creates the unseen observation-instruction pairs via rewriting human-annotated training data. Benefiting from our rewriting mechanism, new observation-instruction pairs can be obtained in both simulator-free and labor-saving manners to promote generalization. Specifically, we first introduce Object-Enriched Observation Rewriting, where we combine Vision-Language Models (VLMs) and Large Language Models (LLMs) to derive rewritten object-enriched scene descriptions, enabling observation synthesis with diverse objects and spatial layouts via Text-to-Image Generation Models (T2IMs). Then, we propose Observation-Contrast Instruction Rewriting, which generates observation-aligned rewritten instructions by requiring LLMs to reason the difference between original and new observations. We further develop a mixing-then-focusing training strategy with a random observation cropping scheme, effectively enhancing data distribution diversity while suppressing augmentation data noise during training. Experiments on both the discrete environments (R2R, REVERIE, and R4R datasets) and continuous environments (R2R-CE dataset) show the superior performance and impressive generalization ability of our method. Code is available at https://github.com/SaDil13/VLN-RAM. |
Accep...Accepted by IEEE Transactions on Neural Networks and Learning Systems |
| UniVLA: Learning to Act Anywhere with Task-centric Latent Actions | 2025-11-03 | ShowA generalist robot should perform effectively across various environments. However, most existing approaches heavily rely on scaling action-annotated data to enhance their capabilities. Consequently, they are often limited to single physical specification and struggle to learn transferable knowledge across different embodiments and environments. To confront these limitations, we propose UniVLA, a new framework for learning cross-embodiment vision-language-action (VLA) policies. Our key innovation is to derive task-centric action representations from videos with a latent action model. This enables us to exploit extensive data across a wide spectrum of embodiments and perspectives. To mitigate the effect of task-irrelevant dynamics, we incorporate language instructions and establish a latent action model within the DINO feature space. Learned from internet-scale videos, the generalist policy can be deployed to various robots through efficient latent action decoding. We obtain state-of-the-art results across multiple manipulation and navigation benchmarks, as well as real-robot deployments. UniVLA achieves superior performance over OpenVLA with less than 1/20 of pretraining compute and 1/10 of downstream data. Continuous performance improvements are observed as heterogeneous data, even including human videos, are incorporated into the training pipeline. The results underscore UniVLA's potential to facilitate scalable and efficient robot policy learning. |
Accep...Accepted to RSS 2025. Code is available at https://github.com/OpenDriveLab/UniVLA |
| "Less is More": Reducing Cognitive Load and Task Drift in Real-Time Multimodal Assistive Agents for the Visually Impaired | 2025-11-02 | ShowVision-Language Models (VLMs) enable on-demand visual assistance, yet current applications for people with visual impairments (PVI) impose high cognitive load and exhibit task drift, limiting real-world utility. We first conducted a formative study with 15 PVI and identified three requirements for visually impaired assistance (VIA): low latency for real-time use, minimal cognitive load, and hallucination-resistant responses to sustain trust. Informed by the formative study, we present VIA-Agent, a prototype that co-optimizes its cognitive 'brain' and interactive 'body'. The brain implements a goal-persistent design with calibrated conciseness to produce brief, actionable guidance; the body adopts a real-time communication (RTC) embodiment-evolving from a request-response model Context Protocol (MCP) pipeline-to-support fluid interaction. We evaluated VIA-Agent with 9 PVI across navigation and object retrieval in the wild against BeMyAI and Doubao. VIA-Agent significantly outperformed BeMyAI both quantitatively and qualitatively. While achieving success rates comparable to Doubao, it reduced mean task time by 39.9% (70.1 s vs. 110.7 s), required fewer conversational turns (4.3 vs. 5.0), and lowered perceived cognitive load and task drift. System Usability Scale (SUS) results aligned with these findings, with VIA-Agent achieving the highest usability. We hope this work inspires the development of more human-centered VIA systems. |
20 pages |
| Fast-SmartWay: Panoramic-Free End-to-End Zero-Shot Vision-and-Language Navigation | 2025-11-02 | ShowRecent advances in Vision-and-Language Navigation in Continuous Environments (VLN-CE) have leveraged multimodal large language models (MLLMs) to achieve zero-shot navigation. However, existing methods often rely on panoramic observations and two-stage pipelines involving waypoint predictors, which introduce significant latency and limit real-world applicability. In this work, we propose Fast-SmartWay, an end-to-end zero-shot VLN-CE framework that eliminates the need for panoramic views and waypoint predictors. Our approach uses only three frontal RGB-D images combined with natural language instructions, enabling MLLMs to directly predict actions. To enhance decision robustness, we introduce an Uncertainty-Aware Reasoning module that integrates (i) a Disambiguation Module for avoiding local optima, and (ii) a Future-Past Bidirectional Reasoning mechanism for globally coherent planning. Experiments on both simulated and real-robot environments demonstrate that our method significantly reduces per-step latency while achieving competitive or superior performance compared to panoramic-view baselines. These results demonstrate the practicality and effectiveness of Fast-SmartWay for real-world zero-shot embodied navigation. |
|
| Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks | 2025-11-02 | ShowHumans possess spatial reasoning abilities that enable them to understand spaces through multimodal observations, such as vision and sound. Large multimodal reasoning models extend these abilities by learning to perceive and reason, showing promising performance across diverse spatial tasks. However, systematic reviews and publicly available benchmarks for these models remain limited. In this survey, we provide a comprehensive review of multimodal spatial reasoning tasks with large models, categorizing recent progress in multimodal large language models (MLLMs) and introducing open benchmarks for evaluation. We begin by outlining general spatial reasoning, focusing on post-training techniques, explainability, and architecture. Beyond classical 2D tasks, we examine spatial relationship reasoning, scene and layout understanding, as well as visual question answering and grounding in 3D space. We also review advances in embodied AI, including vision-language navigation and action models. Additionally, we consider emerging modalities such as audio and egocentric video, which contribute to novel spatial understanding through new sensors. We believe this survey establishes a solid foundation and offers insights into the growing field of multimodal spatial reasoning. Updated information about this survey, codes and implementation of the open benchmarks can be found at https://github.com/zhengxuJosh/Awesome-Spatial-Reasoning. |
|
| MindJourney: Test-Time Scaling with World Models for Spatial Reasoning | 2025-11-01 | ShowSpatial reasoning in 3D space is central to human cognition and indispensable for embodied tasks such as navigation and manipulation. However, state-of-the-art vision-language models (VLMs) struggle frequently with tasks as simple as anticipating how a scene will look after an egocentric motion: they perceive 2D images but lack an internal model of 3D dynamics. We therefore propose MindJourney, a test-time scaling framework that grants a VLM with this missing capability by coupling it to a controllable world model based on video diffusion. The VLM iteratively sketches a concise camera trajectory, while the world model synthesizes the corresponding view at each step. The VLM then reasons over this multi-view evidence gathered during the interactive exploration. Without any fine-tuning, our MindJourney achieves over an average 7.7% performance boost on the representative spatial reasoning benchmark SAT, showing that pairing VLMs with world models for test-time scaling offers a simple, plug-and-play route to robust 3D reasoning. Meanwhile, our method also improves upon the test-time inference VLMs trained through reinforcement learning, which demonstrates the potential of our method that utilizes world models for test-time scaling. |
Proje...Project Page: https://umass-embodied-agi.github.io/MindJourney |
| Continual Vision-and-Language Navigation | 2025-10-31 | ShowDeveloping Vision-and-Language Navigation (VLN) agents typically assumes a \textit{train-once-deploy-once} strategy, which is unrealistic as deployed agents continually encounter novel environments. To address this, we propose the Continual Vision-and-Language Navigation (CVLN) paradigm, where agents learn and adapt incrementally across multiple \textit{scene domains}. CVLN includes two setups: Initial-instruction based CVLN for instruction-following, and Dialogue-based CVLN for dialogue-guided navigation. We also introduce two simple yet effective baselines for sequential decision-making: Perplexity Replay (PerpR), which replays difficult episodes, and Episodic Self-Replay (ESR), which stores and revisits action logits during training. Experiments show that existing continual learning methods fall short for CVLN, while PerpR and ESR achieve better performance by efficiently utilizing replay memory. |
|
| Towards Automated Semantic Interpretability in Reinforcement Learning via Vision-Language Models | 2025-10-31 | ShowSemantic interpretability in Reinforcement Learning (RL) enables transparency and verifiability of decision-making. Achieving semantic interpretability in reinforcement learning requires (1) a feature space composed of human-understandable concepts and (2) a policy that is interpretable and verifiable. However, constructing such a feature space has traditionally relied on manual human specification, which often fails to generalize to unseen environments. Moreover, even when interpretable features are available, most reinforcement learning algorithms employ black-box models as policies, thereby hindering transparency. We introduce interpretable Tree-based Reinforcement learning via Automated Concept Extraction (iTRACE), an automated framework that leverages pre-trained vision-language models (VLM) for semantic feature extraction and train a interpretable tree-based model via RL. To address the impracticality of running VLMs in RL loops, we distill their outputs into a lightweight model. By leveraging Vision-Language Models (VLMs) to automate tree-based reinforcement learning, iTRACE loosens the reliance the need for human annotation that is traditionally required by interpretable models. In addition, it addresses key limitations of VLMs alone, such as their lack of grounding in action spaces and their inability to directly optimize policies. We evaluate iTRACE across three domains: Atari games, grid-world navigation, and driving. The results show that iTRACE outperforms other interpretable policy baselines and matches the performance of black-box policies on the same interpretable feature space. |
|
| ALDEN: Reinforcement Learning for Active Navigation and Evidence Gathering in Long Documents | 2025-10-29 | ShowVision-language models (VLMs) excel at interpreting text-rich images but struggle with long, visually complex documents that demand analysis and integration of information spread across multiple pages. Existing approaches typically rely on fixed reasoning templates or rigid pipelines, which force VLMs into a passive role and hinder both efficiency and generalization. We present Active Long-DocumEnt Navigation (ALDEN), a multi-turn reinforcement learning framework that fine-tunes VLMs as interactive agents capable of actively navigating long, visually rich documents. ALDEN introduces a novel fetch action that directly accesses the page by index, complementing the classic search action and better exploiting document structure. For dense process supervision and efficient training, we propose a rule-based cross-level reward that provides both turn- and token-level signals. To address the empirically observed training instability caused by numerous visual tokens from long documents, we further propose a visual-semantic anchoring mechanism that applies a dual-path KL-divergence constraint to stabilize visual and textual representations separately during training. Trained on a corpus constructed from three open-source datasets, ALDEN achieves state-of-the-art performance on five long-document benchmarks. Overall, ALDEN marks a step beyond passive document reading toward agents that autonomously navigate and reason across long, visually rich documents, offering a robust path to more accurate and efficient long-document understanding. |
|
| SoraNav: Adaptive UAV Task-Centric Navigation via Zeroshot VLM Reasoning | 2025-10-29 | ShowInterpreting visual observations and natural language instructions for complex task execution remains a key challenge in robotics and AI. Despite recent advances, language-driven navigation is still difficult, particularly for UAVs in small-scale 3D environments. Existing Vision-Language Navigation (VLN) approaches are mostly designed for ground robots and struggle to generalize to aerial tasks that require full 3D spatial reasoning. The emergence of large Vision-Language Models (VLMs), such as GPT and Claude, enables zero-shot semantic reasoning from visual and textual inputs. However, these models lack spatial grounding and are not directly applicable to navigation. To address these limitations, SoraNav is introduced, an adaptive UAV navigation framework that integrates zero-shot VLM reasoning with geometry-aware decision-making. Geometric priors are incorporated into image annotations to constrain the VLM action space and improve decision quality. A hybrid switching strategy leverages navigation history to alternate between VLM reasoning and geometry-based exploration, mitigating dead-ends and redundant revisits. A PX4-based hardware-software platform, comprising both a digital twin and a physical micro-UAV, enables reproducible evaluation. Experimental results show that in 2.5D scenarios, our method improves Success Rate (SR) by 25.7% and Success weighted by Path Length (SPL) by 17%. In 3D scenarios, it improves SR by 29.5% and SPL by 18.5% relative to the baseline. |
|
| SCOUT: A Lightweight Framework for Scenario Coverage Assessment in Autonomous Driving | 2025-10-28 | ShowAssessing scenario coverage is crucial for evaluating the robustness of autonomous agents, yet existing methods rely on expensive human annotations or computationally intensive Large Vision-Language Models (LVLMs). These approaches are impractical for large-scale deployment due to cost and efficiency constraints. To address these shortcomings, we propose SCOUT (Scenario Coverage Oversight and Understanding Tool), a lightweight surrogate model designed to predict scenario coverage labels directly from an agent's latent sensor representations. SCOUT is trained through a distillation process, learning to approximate LVLM-generated coverage labels while eliminating the need for continuous LVLM inference or human annotation. By leveraging precomputed perception features, SCOUT avoids redundant computations and enables fast, scalable scenario coverage estimation. We evaluate our method across a large dataset of real-life autonomous navigation scenarios, demonstrating that it maintains high accuracy while significantly reducing computational cost. Our results show that SCOUT provides an effective and practical alternative for large-scale coverage analysis. While its performance depends on the quality of LVLM-generated training labels, SCOUT represents a major step toward efficient scenario coverage oversight in autonomous systems. |
|
| HyPerNav: Hybrid Perception for Object-Oriented Navigation in Unknown Environment | 2025-10-28 | ShowObjective-oriented navigation(ObjNav) enables robot to navigate to target object directly and autonomously in an unknown environment. Effective perception in navigation in unknown environment is critical for autonomous robots. While egocentric observations from RGB-D sensors provide abundant local information, real-time top-down maps offer valuable global context for ObjNav. Nevertheless, the majority of existing studies focus on a single source, seldom integrating these two complementary perceptual modalities, despite the fact that humans naturally attend to both. With the rapid advancement of Vision-Language Models(VLMs), we propose Hybrid Perception Navigation (HyPerNav), leveraging VLMs' strong reasoning and vision-language understanding capabilities to jointly perceive both local and global information to enhance the effectiveness and intelligence of navigation in unknown environments. In both massive simulation evaluation and real-world validation, our methods achieved state-of-the-art performance against popular baselines. Benefiting from hybrid perception approach, our method captures richer cues and finds the objects more effectively, by simultaneously leveraging information understanding from egocentric observations and the top-down map. Our ablation study further proved that either of the hybrid perception contributes to the navigation performance. |
under review |
| Navigation with VLM framework: Towards Going to Any Language | 2025-10-28 | ShowNavigating towards fully open language goals and exploring open scenes in an intelligent way have always raised significant challenges. Recently, Vision Language Models (VLMs) have demonstrated remarkable capabilities to reason with both language and visual data. Although many works have focused on leveraging VLMs for navigation in open scenes, they often require high computational cost, rely on object-centric approaches, or depend on environmental priors in detailed human instructions. We introduce Navigation with VLM (NavVLM), a training-free framework that harnesses open-source VLMs to enable robots to navigate effectively, even for human-friendly language goal such as abstract places, actions, or specific objects in open scenes. NavVLM leverages the VLM as its cognitive core to perceive environmental information and constantly provides exploration guidance achieving intelligent navigation with only a neat target rather than a detailed instruction with environment prior. We evaluated and validated NavVLM in both simulation and real-world experiments. In simulation, our framework achieves state-of-the-art performance in Success weighted by Path Length (SPL) on object-specifc tasks in richly detailed environments from Matterport 3D (MP3D), Habitat Matterport 3D (HM3D) and Gibson. With navigation episode reported, NavVLM demonstrates the capabilities to navigate towards any open-set languages. In real-world validation, we validated our framework's effectiveness in real-world robot at indoor scene. |
under review |
| UrbanVLA: A Vision-Language-Action Model for Urban Micromobility | 2025-10-27 | ShowUrban micromobility applications, such as delivery robots, demand reliable navigation across large-scale urban environments while following long-horizon route instructions. This task is particularly challenging due to the dynamic and unstructured nature of real-world city areas, yet most existing navigation methods remain tailored to short-scale and controllable scenarios. Effective urban micromobility requires two complementary levels of navigation skills: low-level capabilities such as point-goal reaching and obstacle avoidance, and high-level capabilities, such as route-visual alignment. To this end, we propose UrbanVLA, a route-conditioned Vision-Language-Action (VLA) framework designed for scalable urban navigation. Our method explicitly aligns noisy route waypoints with visual observations during execution, and subsequently plans trajectories to drive the robot. To enable UrbanVLA to master both levels of navigation, we employ a two-stage training pipeline. The process begins with Supervised Fine-Tuning (SFT) using simulated environments and trajectories parsed from web videos. This is followed by Reinforcement Fine-Tuning (RFT) on a mixture of simulation and real-world data, which enhances the model's safety and adaptability in real-world settings. Experiments demonstrate that UrbanVLA surpasses strong baselines by more than 55% in the SocialNav task on MetaUrban. Furthermore, UrbanVLA achieves reliable real-world navigation, showcasing both scalability to large-scale urban environments and robustness against real-world uncertainties. |
|
| Can Less Precise Be More Reliable? A Systematic Evaluation of Quantization's Impact on CLIP Beyond Accuracy | 2025-10-27 | ShowThe powerful zero-shot generalization capabilities of vision-language models (VLMs) like CLIP have enabled new paradigms for safety-related tasks such as out-of-distribution (OOD) detection. However, additional aspects crucial for the computationally efficient and reliable deployment of CLIP are still overlooked. In particular, the impact of quantization on CLIP's performance beyond accuracy remains underexplored. This work presents a large-scale evaluation of quantization on CLIP models, assessing not only in-distribution accuracy but a comprehensive suite of reliability metrics and revealing counterintuitive results driven by pre-training source. We demonstrate that quantization consistently improves calibration for typically underconfident pre-trained models, while often degrading it for overconfident variants. Intriguingly, this degradation in calibration does not preclude gains in other reliability metrics; we find that OOD detection can still improve for these same poorly calibrated models. Furthermore, we identify specific quantization-aware training (QAT) methods that yield simultaneous gains in zero-shot accuracy, calibration, and OOD robustness, challenging the view of a strict efficiency-performance trade-off. These findings offer critical insights for navigating the multi-objective problem of deploying efficient, reliable, and robust VLMs by utilizing quantization beyond its conventional role. |
Prepr...Preprint, under peer review |
| STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization | 2025-10-27 | ShowThe Zero-shot Vision-and-Language Navigation in Continuous Environments (VLN-CE) task requires agents to navigate previously unseen 3D environments using natural language instructions, without any scene-specific training. A critical challenge in this setting lies in ensuring agents' actions align with both spatial structure and task intent over long-horizon execution. Existing methods often fail to achieve robust navigation due to a lack of structured decision-making and insufficient integration of feedback from previous actions. To address these challenges, we propose STRIDER (Instruction-Aligned Structural Decision Space Optimization), a novel framework that systematically optimizes the agent's decision space by integrating spatial layout priors and dynamic task feedback. Our approach introduces two key innovations: 1) a Structured Waypoint Generator that constrains the action space through spatial structure, and 2) a Task-Alignment Regulator that adjusts behavior based on task progress, ensuring semantic alignment throughout navigation. Extensive experiments on the R2R-CE and RxR-CE benchmarks demonstrate that STRIDER significantly outperforms strong SOTA across key metrics; in particular, it improves Success Rate (SR) from 29% to 35%, a relative gain of 20.7%. Such results highlight the importance of spatially constrained decision-making and feedback-guided execution in improving navigation fidelity for zero-shot VLN-CE. |
|
| Hierarchical Language Models for Semantic Navigation and Manipulation in an Aerial-Ground Robotic System | 2025-10-27 | ShowHeterogeneous multirobot systems show great potential in complex tasks requiring coordinated hybrid cooperation. However, existing methods that rely on static or task-specific models often lack generalizability across diverse tasks and dynamic environments. This highlights the need for generalizable intelligence that can bridge high-level reasoning with low-level execution across heterogeneous agents. To address this, we propose a hierarchical multimodal framework that integrates a prompted large language model (LLM) with a fine-tuned vision-language model (VLM). At the system level, the LLM performs hierarchical task decomposition and constructs a global semantic map, while the VLM provides semantic perception and object localization, where the proposed GridMask significantly enhances the VLM's spatial accuracy for reliable fine-grained manipulation. The aerial robot leverages this global map to generate semantic paths and guide the ground robot's local navigation and manipulation, ensuring robust coordination even in target-absent or ambiguous scenarios. We validate the framework through extensive simulation and real-world experiments on long-horizon object arrangement tasks, demonstrating zero-shot adaptability, robust semantic navigation, and reliable manipulation in dynamic environments. To the best of our knowledge, this work presents the first heterogeneous aerial-ground robotic system that integrates VLM-based perception with LLM-driven reasoning for global high-level task planning and execution. |
18 pages, 10 figures |
| Open-Set 3D Semantic Instance Maps for Vision Language Navigation -- O3D-SIM | 2025-10-25 | ShowHumans excel at forming mental maps of their surroundings, equipping them to understand object relationships and navigate based on language queries. Our previous work, SI Maps (Nanwani L, Agarwal A, Jain K, et al. Instance-level semantic maps for vision language navigation. In: 2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN). IEEE; 2023 Aug.), showed that having instance-level information and the semantic understanding of an environment helps significantly improve performance for language-guided tasks. We extend this instance-level approach to 3D while increasing the pipeline's robustness and improving quantitative and qualitative results. Our method leverages foundational models for object recognition, image segmentation, and feature extraction. We propose a representation that results in a 3D point cloud map with instance-level embeddings, which bring in the semantic understanding that natural language commands can query. Quantitatively, the work improves upon the success rate of language-guided tasks. At the same time, we qualitatively observe the ability to identify instances more clearly and leverage the foundational models and language and image-aligned embeddings to identify objects that, otherwise, a closed-set approach wouldn't be able to identify. Project Page - https://smart-wheelchair-rrc.github.io/o3d-sim-webpage |
|
| VAMOS: A Hierarchical Vision-Language-Action Model for Capability-Modulated and Steerable Navigation | 2025-10-23 | ShowA fundamental challenge in robot navigation lies in learning policies that generalize across diverse environments while conforming to the unique physical constraints and capabilities of a specific embodiment (e.g., quadrupeds can walk up stairs, but rovers cannot). We propose VAMOS, a hierarchical VLA that decouples semantic planning from embodiment grounding: a generalist planner learns from diverse, open-world data, while a specialist affordance model learns the robot's physical constraints and capabilities in safe, low-cost simulation. We enabled this separation by carefully designing an interface that lets a high-level planner propose candidate paths directly in image space that the affordance model then evaluates and re-ranks. Our real-world experiments show that VAMOS achieves higher success rates in both indoor and complex outdoor navigation than state-of-the-art model-based and end-to-end learning methods. We also show that our hierarchical design enables cross-embodied navigation across legged and wheeled robots and is easily steerable using natural language. Real-world ablations confirm that the specialist model is key to embodiment grounding, enabling a single high-level planner to be deployed across physically distinct wheeled and legged robots. Finally, this model significantly enhances single-robot reliability, achieving 3X higher success rates by rejecting physically infeasible plans. Website: https://vamos-vla.github.io/ |
|
| mmWalk: Towards Multi-modal Multi-view Walking Assistance | 2025-10-23 | ShowWalking assistance in extreme or complex environments remains a significant challenge for people with blindness or low vision (BLV), largely due to the lack of a holistic scene understanding. Motivated by the real-world needs of the BLV community, we build mmWalk, a simulated multi-modal dataset that integrates multi-view sensor and accessibility-oriented features for outdoor safe navigation. Our dataset comprises 120 manually controlled, scenario-categorized walking trajectories with 62k synchronized frames. It contains over 559k panoramic images across RGB, depth, and semantic modalities. Furthermore, to emphasize real-world relevance, each trajectory involves outdoor corner cases and accessibility-specific landmarks for BLV users. Additionally, we generate mmWalkVQA, a VQA benchmark with over 69k visual question-answer triplets across 9 categories tailored for safe and informed walking assistance. We evaluate state-of-the-art Vision-Language Models (VLMs) using zero- and few-shot settings and found they struggle with our risk assessment and navigational tasks. We validate our mmWalk-finetuned model on real-world datasets and show the effectiveness of our dataset for advancing multi-modal walking assistance. |
Accep...Accepted by NeurIPS 2025 Datasets and Benchmarks Track. Data and Code: https://github.com/KediYing/mmWalk |
| Title | Date | Abstract | Comment |
|---|---|---|---|
| Training-Time Action Conditioning for Efficient Real-Time Chunking | 2025-12-05 | ShowReal-time chunking (RTC) enables vision-language-action models (VLAs) to generate smooth, reactive robot trajectories by asynchronously predicting action chunks and conditioning on previously committed actions via inference-time inpainting. However, this inpainting method introduces computational overhead that increases inference latency. In this work, we propose a simple alternative: simulating inference delay at training time and conditioning on action prefixes directly, eliminating any inference-time overhead. Our method requires no modifications to the model architecture or robot runtime, and can be implemented with only a few additional lines of code. In simulated experiments, we find that training-time RTC outperforms inference-time RTC at higher inference delays. In real-world experiments on box building and espresso making tasks with the |
|
| SIMPACT: Simulation-Enabled Action Planning using Vision-Language Models | 2025-12-05 | ShowVision-Language Models (VLMs) exhibit remarkable common-sense and semantic reasoning capabilities. However, they lack a grounded understanding of physical dynamics. This limitation arises from training VLMs on static internet-scale visual-language data that contain no causal interactions or action-conditioned changes. Consequently, it remains challenging to leverage VLMs for fine-grained robotic manipulation tasks that require physical understanding, reasoning, and corresponding action planning. To overcome this, we present SIMPACT, a test-time, SIMulation-enabled ACTion Planning framework that equips VLMs with physical reasoning through simulation-in-the-loop world modeling, without requiring any additional training. From a single RGB-D observation, SIMPACT efficiently constructs physics simulations, enabling the VLM to propose informed actions, observe simulated rollouts, and iteratively refine its reasoning. By integrating language reasoning with physics prediction, our simulation-enabled VLM can understand contact dynamics and action outcomes in a physically grounded way. Our method demonstrates state-of-the-art performance on five challenging, real-world rigid-body and deformable manipulation tasks that require fine-grained physical reasoning, outperforming existing general-purpose robotic manipulation models. Our results demonstrate that embedding physics understanding via efficient simulation into VLM reasoning at test time offers a promising path towards generalizable embodied intelligence. Project webpage can be found at https://simpact-bot.github.io |
|
| TRACE: A Framework for Analyzing and Enhancing Stepwise Reasoning in Vision-Language Models | 2025-12-05 | ShowReliable mathematical and scientific reasoning remains an open challenge for large vision-language models. Standard final-answer evaluation often masks reasoning errors, allowing silent failures to persist. To address this gap, we introduce TRACE, a framework for Transparent Reasoning And Consistency Evaluation that diagnoses reasoning trajectories rather than only end results. At its core, TRACE leverages Auxiliary Reasoning Sets, compact sub question answer pairs that decompose complex problems, evaluate intermediate steps through consistency-based metrics, and expose failures overlooked by standard evaluation. Our experiments show that consistency across ARS correlates with final-answer correctness and helps pinpoint the reasoning steps where failures arise, offering actionable signals for model improvement. Furthermore, TRACE defines confidence regions that distinguish reliable from unreliable reasoning paths, supporting effective filtering, debugging, and model refinement. |
|
| Probing the effectiveness of World Models for Spatial Reasoning through Test-time Scaling | 2025-12-05 | ShowVision-Language Models (VLMs) remain limited in spatial reasoning tasks that require multi-view understanding and embodied perspective shifts. Recent approaches such as MindJourney attempt to mitigate this gap through test-time scaling where a world model imagines action-conditioned trajectories and a heuristic verifier selects helpful views from such trajectories. In this work, we systematically examine how such test-time verifiers behave across benchmarks, uncovering both their promise and their pitfalls. Our uncertainty-based analyses show that MindJourney's verifier provides little meaningful calibration, and that random scoring often reduces answer entropy equally well, thus exposing systematic action biases and unreliable reward signals. To mitigate these, we introduce a Verification through Spatial Assertions (ViSA) framework that grounds the test-time reward in verifiable, frame-anchored micro-claims. This principled verifier consistently improves spatial reasoning on the SAT-Real benchmark and corrects trajectory-selection biases through more balanced exploratory behavior. However, on the challenging MMSI-Bench, none of the verifiers, including ours, achieve consistent scaling, suggesting that the current world models form an information bottleneck where imagined views fail to enrich fine-grained reasoning. Together, these findings chart the bad, good, and ugly aspects of test-time verification for world-model-based reasoning. Our code is available at https://github.com/chandar-lab/visa-for-mindjourney. |
Exten...Extended abstract at World Modeling Workshop 2026 |
| HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policies | 2025-12-05 | ShowThe development of foundation models for embodied intelligence critically depends on access to large-scale, high-quality robot demonstration data. Recent approaches have sought to address this challenge by training on large collections of heterogeneous robotic datasets. However, unlike vision or language data, robotic demonstrations exhibit substantial heterogeneity across embodiments and action spaces as well as other prominent variations such as senor configurations and action control frequencies. The lack of explicit designs for handling such heterogeneity causes existing methods to struggle with integrating diverse factors, thereby limiting their generalization and leading to degraded performance when transferred to new settings. In this paper, we present HiMoE-VLA, a novel vision-language-action (VLA) framework tailored to effectively handle diverse robotic data with heterogeneity. Specifically, we introduce a Hierarchical Mixture-of-Experts (HiMoE) architecture for the action module which adaptively handles multiple sources of heterogeneity across layers and gradually abstracts them into shared knowledge representations. Through extensive experimentation with simulation benchmarks and real-world robotic platforms, HiMoE-VLA demonstrates a consistent performance boost over existing VLA baselines, achieving higher accuracy and robust generalization across diverse robots and action spaces. The code and models are publicly available at https://github.com/ZhiyingDu/HiMoE-VLA. |
|
| ReSem3D: Refinable 3D Spatial Constraints via Fine-Grained Semantic Grounding for Generalizable Robotic Manipulation | 2025-12-05 | ShowSemantics-driven 3D spatial constraints align highlevel semantic representations with low-level action spaces, facilitating the unification of task understanding and execution in robotic manipulation. The synergistic reasoning of Multimodal Large Language Models (MLLMs) and Vision Foundation Models (VFMs) enables cross-modal 3D spatial constraint construction. Nevertheless, existing methods have three key limitations: (1) coarse semantic granularity in constraint modeling, (2) lack of real-time closed-loop planning, (3) compromised robustness in semantically diverse environments. To address these challenges, we propose ReSem3D, a unified manipulation framework for semantically diverse environments, leveraging the synergy between VFMs and MLLMs to achieve fine-grained visual grounding and dynamically constructs hierarchical 3D spatial constraints for real-time manipulation. Specifically, the framework is driven by hierarchical recursive reasoning in MLLMs, which interact with VFMs to automatically construct 3D spatial constraints from natural language instructions and RGB-D observations in two stages: part-level extraction and region-level refinement. Subsequently, these constraints are encoded as real-time optimization objectives in joint space, enabling reactive behavior to dynamic disturbances. Extensive simulation and real-world experiments are conducted in semantically rich household and sparse chemical lab environments. The results demonstrate that ReSem3D performs diverse manipulation tasks under zero-shot conditions, exhibiting strong adaptability and generalization. Code and videos are available at https://github.com/scy-v/ReSem3D and https://resem3d.github.io. |
12 pages,9 figures |
| Conscious Gaze: Adaptive Attention Mechanisms for Hallucination Mitigation in Vision-Language Models | 2025-12-05 | ShowLarge Vision-Language Models (VLMs) often exhibit text inertia, where attention drifts from visual evidence toward linguistic priors, resulting in object hallucinations. Existing decoding strategies intervene only at the output logits and thus cannot correct internal reasoning drift, while recent internal-control methods based on heuristic head suppression or global steering vectors lack principled grounding. We introduce Conscious Gaze (CG-VLM), a training-free, inference-time framework that converts game-theoretic interpretability into actionable decoding control. A Cognitive Demand Sensor built on Harsanyi interactions estimates instantaneous vision-text synergy and identifies moments when visual grounding is necessary. Conditioned on this signal, a Focused Consensus Induction module selectively reorients mid-layer attention toward visual tokens before collapse into text priors. CG-VLM achieves state-of-the-art results on POPE and CHAIR across InstructBLIP, LLaVA, Qwen-VL, and mPLUG, while preserving general capabilities, demonstrating that token-level sensing enables precise, context-aware intervention without compromising foundational knowledge. |
6 pages, 6 figures |
| VOST-SGG: VLM-Aided One-Stage Spatio-Temporal Scene Graph Generation | 2025-12-05 | ShowSpatio-temporal scene graph generation (ST-SGG) aims to model objects and their evolving relationships across video frames, enabling interpretable representations for downstream reasoning tasks such as video captioning and visual question answering. Despite recent advancements in DETR-style single-stage ST-SGG models, they still suffer from several key limitations. First, while these models rely on attention-based learnable queries as a core component, these learnable queries are semantically uninformed and instance-agnostically initialized. Second, these models rely exclusively on unimodal visual features for predicate classification. To address these challenges, we propose VOST-SGG, a VLM-aided one-stage ST-SGG framework that integrates the common sense reasoning capabilities of vision-language models (VLMs) into the ST-SGG pipeline. First, we introduce the dual-source query initialization strategy that disentangles what to attend to from where to attend, enabling semantically grounded what-where reasoning. Furthermore, we propose a multi-modal feature bank that fuses visual, textual, and spatial cues derived from VLMs for improved predicate classification. Extensive experiments on the Action Genome dataset demonstrate that our approach achieves state-of-the-art performance, validating the effectiveness of integrating VLM-aided semantic priors and multi-modal features for ST-SGG. We will release the code at https://github.com/LUNAProject22/VOST. |
|
| Real-Time Execution of Action Chunking Flow Policies | 2025-12-05 | ShowModern AI systems, especially those interacting with the physical world, increasingly require real-time performance. However, the high latency of state-of-the-art generalist models, including recent vision-language action models (VLAs), poses a significant challenge. While action chunking has enabled temporal consistency in high-frequency control tasks, it does not fully address the latency problem, leading to pauses or out-of-distribution jerky movements at chunk boundaries. This paper presents a novel inference-time algorithm that enables smooth asynchronous execution of action chunking policies. Our method, real-time chunking (RTC), is applicable to any diffusion- or flow-based VLA out of the box with no re-training. It generates the next action chunk while executing the current one, "freezing" actions guaranteed to execute and "inpainting" the rest. To test RTC, we introduce a new benchmark of 12 highly dynamic tasks in the Kinetix simulator, as well as evaluate 6 challenging real-world bimanual manipulation tasks. Results demonstrate that RTC is fast, performant, and uniquely robust to inference delay, significantly improving task throughput and enabling high success rates in precise tasks |
publi...published in NeurIPS 2025 |
| Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment | 2025-12-05 | ShowVision-Language-Action (VLA) models have emerged as a powerful framework that unifies perception, language, and control, enabling robots to perform diverse tasks through multimodal understanding. However, current VLA models typically contain massive parameters and rely heavily on large-scale robot data pretraining, leading to high computational costs during training, as well as limited deployability for real-time inference. Moreover, most training paradigms often degrade the perceptual representations of the vision-language backbone, resulting in overfitting and poor generalization to downstream tasks. In this work, we present Evo-1, a lightweight VLA model that reduces computation and improves deployment efficiency, while maintaining strong performance without pretraining on robot data. Evo-1 builds on a native multimodal Vision-Language model (VLM), incorporating a novel cross-modulated diffusion transformer along with an optimized integration module, together forming an effective architecture. We further introduce a two-stage training paradigm that progressively aligns action with perception, preserving the representations of the VLM. Notably, with only 0.77 billion parameters, Evo-1 achieves state-of-the-art results on the Meta-World and RoboTwin suite, surpassing the previous best models by 12.4% and 6.9%, respectively, and also attains a competitive result of 94.8% on LIBERO. In real-world evaluations, Evo-1 attains a 78% success rate with high inference frequency and low memory overhead, outperforming all baseline methods. We release code, data, and model weights to facilitate future research on lightweight and efficient VLA models. |
Githu... |
| Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views | 2025-12-05 | ShowForecasting how human hands move in egocentric views is critical for applications like augmented reality and human-robot policy transfer. Recently, several hand trajectory prediction (HTP) methods have been developed to generate future possible hand waypoints, which still suffer from insufficient prediction targets, inherent modality gaps, entangled hand-head motion, and limited validation in downstream tasks. To address these limitations, we present a universal hand motion forecasting framework considering multi-modal input, multi-dimensional and multi-target prediction patterns, and multi-task affordances for downstream applications. We harmonize multiple modalities by vision-language fusion, global context incorporation, and task-aware text embedding injection, to forecast hand waypoints in both 2D and 3D spaces. A novel dual-branch diffusion is proposed to concurrently predict human head and hand movements, capturing their motion synergy in egocentric vision. By introducing target indicators, the prediction model can forecast the specific joint waypoints of the wrist or the fingers, besides the widely studied hand center points. In addition, we enable Uni-Hand to additionally predict hand-object interaction states (contact/separation) to facilitate downstream tasks better. As the first work to incorporate downstream task evaluation in the literature, we build novel benchmarks to assess the real-world applicability of hand motion forecasting algorithms. The experimental results on multiple publicly available datasets and our newly proposed benchmarks demonstrate that Uni-Hand achieves the state-of-the-art performance in multi-dimensional and multi-target hand motion forecasting. Extensive validation in multiple downstream tasks also presents its impressive human-robot policy transfer to enable robotic manipulation, and effective feature enhancement for action anticipation/recognition. |
Exten...Extended journal version of MMTwin (IROS'25). Code and data: https://github.com/IRMVLab/UniHand |
| From Segments to Scenes: Temporal Understanding in Autonomous Driving via Vision-Language Model | 2025-12-04 | ShowTemporal understanding in autonomous driving (AD) remains a significant challenge, even for recent state-of-the-art (SoTA) Vision-Language Models (VLMs). Prior work has introduced datasets and benchmarks aimed at improving temporal reasoning, but these have emphasized other video content, including sports, cooking, and movies. No existing benchmark focuses exclusively on the unique challenges of temporal understanding in ego-centric AD footage. To fill this gap, the Temporal Understanding in Autonomous Driving (TAD) benchmark is presented, which evaluates VLMs' ability to capture the dynamic relationships between actions in AD. TAD comprises nearly 6,000 question-answer (QA) pairs, spanning 7 human-designed tasks. In addition, an evaluation is performed that consists of 9 closed- and open-source generalist models as well as SoTA AD specialist models. When applied to TAD, current SoTA models demonstrated substandard accuracies, largely due to imperfect fine-grained motion understanding. To improve motion understanding and overall accuracy on TAD, two novel training-free solutions are proposed: Scene-CoT, that leverages Chain-of-Thought (CoT) and TCogMap, which incorporates an ego-centric temporal cognitive map. The proposed approaches are integrated with existing VLMs and improve average accuracy on TAD by up to 17.72%. By introducing TAD, benchmarking multiple SoTA models, and proposing effective enhancements, this work aims to catalyze future research on temporal understanding in AD. The benchmark and evaluation code are available at \href{https://huggingface.co/datasets/vbdai/TAD}{Hugging Face} and \href{https://github.com/vbdi/tad_bench}{Github}, respectively. |
|
| SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control | 2025-12-04 | ShowDespite the rise of billion-parameter foundation models trained across thousands of GPUs, similar scaling gains have not been shown for humanoid control. Current neural controllers for humanoids remain modest in size, target a limited set of behaviors, and are trained on a handful of GPUs over several days. We show that scaling up model capacity, data, and compute yields a generalist humanoid controller capable of creating natural and robust whole-body movements. Specifically, we posit motion tracking as a natural and scalable task for humanoid control, leveraging dense supervision from diverse motion-capture data to acquire human motion priors without manual reward engineering. We build a foundation model for motion tracking by scaling along three axes: network size (from 1.2M to 42M parameters), dataset volume (over 100M frames, 700 hours of high-quality motion data), and compute (9k GPU hours). Beyond demonstrating the benefits of scale, we show the practical utility of our model through two mechanisms: (1) a real-time universal kinematic planner that bridges motion tracking to downstream task execution, enabling natural and interactive control, and (2) a unified token space that supports various motion input interfaces, such as VR teleoperation devices, human videos, and vision-language-action (VLA) models, all using the same policy. Scaling motion tracking exhibits favorable properties: performance improves steadily with increased compute and data diversity, and learned representations generalize to unseen motions, establishing motion tracking at scale as a practical foundation for humanoid control. |
Proje...Project page: https://nvlabs.github.io/SONIC/ |
| STARE-VLA: Progressive Stage-Aware Reinforcement for Fine-Tuning Vision-Language-Action Models | 2025-12-04 | ShowRecent advances in Vision-Language-Action (VLA) models, powered by large language models and reinforcement learning-based fine-tuning, have shown remarkable progress in robotic manipulation. Existing methods often treat long-horizon actions as linguistic sequences and apply trajectory-level optimization methods such as Trajectory-wise Preference Optimization (TPO) or Proximal Policy Optimization (PPO), leading to coarse credit assignment and unstable training. However, unlike language, where a unified semantic meaning is preserved despite flexible sentence order, action trajectories progress through causally chained stages with different learning difficulties. This motivates progressive stage optimization. Thereby, we present Stage-Aware Reinforcement (STARE), a module that decomposes a long-horizon action trajectory into semantically meaningful stages and provides dense, interpretable, and stage-aligned reinforcement signals. Integrating STARE into TPO and PPO, we yield Stage-Aware TPO (STA-TPO) and Stage-Aware PPO (STA-PPO) for offline stage-wise preference and online intra-stage interaction, respectively. Further building on supervised fine-tuning as initialization, we propose the Imitation -> Preference -> Interaction (IPI), a serial fine-tuning pipeline for improving action accuracy in VLA models. Experiments on SimplerEnv and ManiSkill3 demonstrate substantial gains, achieving state-of-the-art success rates of 98.0 percent on SimplerEnv and 96.4 percent on ManiSkill3 tasks. |
|
| TV2TV: A Unified Framework for Interleaved Language and Video Generation | 2025-12-04 | ShowVideo generation models are rapidly advancing, but can still struggle with complex video outputs that require significant semantic branching or repeated high-level reasoning about what should happen next. In this paper, we introduce a new class of omni video-text models that integrate ideas from recent LM reasoning advances to address this challenge. More specifically, we present TV2TV, a unified generative modeling framework which decomposes video generation into an interleaved text and video generation process. TV2TV jointly learns language modeling (next-token prediction) and video flow matching (next-frame prediction) using a Mixture-of-Transformers (MoT) architecture. At inference time, TV2TV decides when to alternate between generating text and video frames, allowing the model to "think in words" about subsequent content before ``acting in pixels'' to produce frames. This design offloads much of the responsibility for deciding what should happen next to the language modeling tower, enabling improved visual quality and prompt alignment of generated videos. It also enables fine-grained controllability, allowing users to modify the video generation trajectory through text interventions at any point in the process. In controlled experiments on video game data, TV2TV demonstrates substantial improvements in both visual quality and controllability. TV2TV also scales to natural videos, as we show by augmenting sports videos with interleaved natural language action descriptions using vision-language models (VLMs). Training TV2TV on this corpus yields strong visual quality and prompt alignment, showcasing the model's ability to reason about and generate complex real-world action sequences. Together, these results highlight TV2TV as a promising step toward video generation with open-ended textual reasoning and control. |
|
| FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via neural Action Tokenization | 2025-12-04 | ShowAutoregressive vision-language-action (VLA) models have recently demonstrated strong capabilities in robotic manipulation. However, their core process of action tokenization often involves a trade-off between reconstruction fidelity and inference efficiency. We introduce FASTer, a unified framework for efficient and generalizable robot learning that integrates a learnable tokenizer with an autoregressive policy built upon it. FASTerVQ encodes action chunks as single-channel images, capturing global spatio-temporal dependencies while maintaining a high compression ratio. FASTerVLA builds on this tokenizer with block-wise autoregressive decoding and a lightweight action expert, achieving both faster inference and higher task performance. Extensive experiments across simulated and real-world benchmarks show that FASTerVQ delivers superior reconstruction quality, high token utilization, and strong cross-task and cross-embodiment generalization, while FASTerVLA further improves overall capability, surpassing previous state-of-the-art VLA models in both inference speed and task performance. |
|
| GigaBrain-0: A World Model-Powered Vision-Language-Action Model | 2025-12-04 | ShowTraining Vision-Language-Action (VLA) models for generalist robots typically requires large-scale real-world robot data, which is expensive and time-consuming to collect. The inefficiency of physical data collection severely limits the scalability, and generalization capacity of current VLA systems. To address this challenge, we introduce GigaBrain-0, a novel VLA foundation model empowered by world model-generated data (e.g., video generation, real2real transfer, human transfer, view transfer, sim2real transfer data). By leveraging world models to generate diverse data at scale, GigaBrain-0 significantly reduces reliance on real robot data while improving cross-task generalization. Our approach further improves policy robustness through RGBD input modeling and embodied Chain-of-Thought (CoT) supervision, enabling the model to reason about spatial geometry, object states, and long-horizon dependencies during task execution. This leads to substantial gains in real-world performance on dexterous, long-horizon, and mobile manipulation tasks. Extensive experiments demonstrate that GigaBrain-0 achieves superior generalization across variations in appearances (e.g., textures, colors), object placements, and camera viewpoints. Additionally, we present GigaBrain-0-Small, an optimized lightweight variant designed to run efficiently on devices such as the NVIDIA Jetson AGX Orin. |
https... |
| E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Driving | 2025-12-04 | ShowEnd-to-end autonomous driving (AD) systems increasingly adopt vision-language-action (VLA) models, yet they typically ignore the passenger's emotional state, which is central to comfort and AD acceptance. We introduce Open-Domain End-to-End (OD-E2E) autonomous driving, where an autonomous vehicle (AV) must interpret free-form natural-language commands, infer the emotion, and plan a physically feasible trajectory. We propose E3AD, an emotion-aware VLA framework that augments semantic understanding with two cognitively inspired components: a continuous Valenc-Arousal-Dominance (VAD) emotion model that captures tone and urgency from language, and a dual-pathway spatial reasoning module that fuses egocentric and allocentric views for human-like spatial cognition. A consistency-oriented training scheme, combining modality pretraining with preference-based alignment, further enforces coherence between emotional intent and driving actions. Across real-world datasets, E3AD improves visual grounding and waypoint planning and achieves state-of-the-art (SOTA) VAD correlation for emotion estimation. These results show that injecting emotion into VLA-style driving yields more human-aligned grounding, planning, and human-centric feedback. |
|
| Towards Cross-View Point Correspondence in Vision-Language Models | 2025-12-04 | ShowCross-view correspondence is a fundamental capability for spatial understanding and embodied AI. However, it is still far from being realized in Vision-Language Models (VLMs), especially in achieving precise point-level correspondence, which is crucial for precise affordance interaction. So we propose the Cross-View Point Correspondence (CVPC) task and CrossPoint-Bench, a comprehensive benchmark with hierarchical design, inspired by the human cognitive process of "perceive", "reason", and "correspond". Our evaluation shows the state-of-the-art models (e.g., Gemini-2.5-Pro) still fall far behind humans, with a gap of over 54.65% in overall accuracy, exposing a challenge in transitioning from coarse-grained judgement to fine-grained coordinate prediction. To address this problem, we construct CrossPoint-378K, a dataset with 378K question-answering pairs across 900 scenes, focused on actionable affordance regions that better reflect real-world manipulation and interaction scenarios. Furthermore, we propose CroPond that trained on the CrossPoint-378K dataset. Our CroPond achieves state-of-the-art performance on CrossPoint-Bench, surpassing Gemini-2.5-Pro by 39.7% accuracy, which offers a foundation for advancing future work on cross-view correspondence. The benchmark, dataset, and model are publicly available at https://github.com/WangYipu2002/CrossPoint. |
|
| ThaiOCRBench: A Task-Diverse Benchmark for Vision-Language Understanding in Thai | 2025-12-04 | ShowWe present ThaiOCRBench, the first comprehensive benchmark for evaluating vision-language models (VLMs) on Thai text-rich visual understanding tasks. Despite recent progress in multimodal modeling, existing benchmarks predominantly focus on high-resource languages, leaving Thai underrepresented, especially in tasks requiring document structure understanding. ThaiOCRBench addresses this gap by offering a diverse, human-annotated dataset comprising 2,808 samples across 13 task categories. We evaluate a wide range of state-of-the-art VLMs in a zero-shot setting, spanning both proprietary and open-source systems. Results show a significant performance gap, with proprietary models (e.g., Gemini 2.5 Pro) outperforming open-source counterparts. Notably, fine-grained text recognition and handwritten content extraction exhibit the steepest performance drops among open-source models. Through detailed error analysis, we identify key challenges such as language bias, structural mismatch, and hallucinated content. ThaiOCRBench provides a standardized framework for assessing VLMs in low-resource, script-complex settings, and provides actionable insights for improving Thai-language document understanding. |
Accep...Accepted at IJCNLP-AACL 2025 (Main). This version includes the corrected Table 2 and an updated conclusion regarding the deletion count of the Gemma model |
| SAM3-I: Segment Anything with Instructions | 2025-12-04 | ShowSegment Anything Model 3 (SAM3) has advanced open-vocabulary segmentation through promptable concept segmentation, allowing users to segment all instances corresponding to a given concept, typically specified with short noun-phrase (NP) prompts. While this marks the first integration of language-level concepts within the SAM family, real-world usage typically requires far richer expressions that include attributes, spatial relations, functionalities, actions, states, and even implicit reasoning over instances. Currently, SAM3 relies on external multi-modal agents to convert complex instructions into NPs and then conduct iterative mask filtering. However, these NP-level concepts remain overly coarse, often failing to precisely represent a specific instance. In this work, we present SAM3-I, an enhanced framework that unifies concept-level understanding and instruction-level reasoning within the SAM family. SAM3-I introduces an instruction-aware cascaded adaptation mechanism that progressively aligns expressive instruction semantics with SAM3's existing vision-language representations, enabling direct instruction-following segmentation without sacrificing its original concept-driven capabilities. Furthermore, we design a structured instruction taxonomy spanning concept, simple, and complex levels, and develop a scalable data engine to construct a dataset with diverse instruction-mask pairs. Experiments show that SAM3-I delivers appealing performance, demonstrating that SAM3 can be effectively extended to follow natural-language instructions while preserving its strong concept grounding. We open-source SAM3-I and provide practical fine-tuning workflows, enabling researchers to adapt it to domain-specific applications. The source code is available here. |
Preli...Preliminary results; work in progress |
| X-Humanoid: Robotize Human Videos to Generate Humanoid Videos at Scale | 2025-12-04 | ShowThe advancement of embodied AI has unlocked significant potential for intelligent humanoid robots. However, progress in both Vision-Language-Action (VLA) models and world models is severely hampered by the scarcity of large-scale, diverse training data. A promising solution is to "robotize" web-scale human videos, which has been proven effective for policy training. However, these solutions mainly "overlay" robot arms to egocentric videos, which cannot handle complex full-body motions and scene occlusions in third-person videos, making them unsuitable for robotizing humans. To bridge this gap, we introduce X-Humanoid, a generative video editing approach that adapts the powerful Wan 2.2 model into a video-to-video structure and finetunes it for the human-to-humanoid translation task. This finetuning requires paired human-humanoid videos, so we designed a scalable data creation pipeline, turning community assets into 17+ hours of paired synthetic videos using Unreal Engine. We then apply our trained model to 60 hours of the Ego-Exo4D videos, generating and releasing a new large-scale dataset of over 3.6 million "robotized" humanoid video frames. Quantitative analysis and user studies confirm our method's superiority over existing baselines: 69% of users rated it best for motion consistency, and 62.1% for embodiment correctness. |
|
| dVLM-AD: Enhance Diffusion Vision-Language-Model for Driving via Controllable Reasoning | 2025-12-04 | ShowThe autonomous driving community is increasingly focused on addressing the challenges posed by out-of-distribution (OOD) driving scenarios. A dominant research trend seeks to enhance end-to-end (E2E) driving systems by integrating vision-language models (VLMs), leveraging their rich world knowledge and reasoning abilities to improve generalization across diverse environments. However, most existing VLMs or vision-language agents (VLAs) are built upon autoregressive (AR) models. In this paper, we observe that existing AR-based VLMs -- limited by causal attention and sequential token generation -- often fail to maintain consistency and controllability between high-level reasoning and low-level planning. In contrast, recent discrete diffusion VLMs equipped with bidirectional attention exhibit superior controllability and reliability through iterative denoising. Building on these observations, we introduce dVLM-AD, a diffusion-based vision-language model that unifies perception, structured reasoning, and low-level planning for end-to-end driving. Evaluated on nuScenes and WOD-E2E, dVLM-AD yields more consistent reasoning-action pairs and achieves planning performance comparable to existing driving VLM/VLA systems despite a modest backbone, outperforming AR-based baselines with a 9 percent improvement in behavior-trajectory consistency and a 6 percent increase in RFS on long-tail WOD-E2E scenarios. These results suggest a controllable and reliable pathway for scalable end-to-end driving. |
|
| Vision-Language-Action Models for Selective Robotic Disassembly: A Case Study on Critical Component Extraction from Desktops | 2025-12-04 | ShowAutomating disassembly of critical components from end-of-life (EoL) desktops, such as high-value items like RAM modules and CPUs, as well as sensitive parts like hard disk drives, remains challenging due to the inherent variability and uncertainty of these products. Moreover, their disassembly requires sequential, precise, and dexterous operations, further increasing the complexity of automation. Current robotic disassembly processes are typically divided into several stages: perception, sequence planning, task planning, motion planning, and manipulation. Each stage requires explicit modeling, which limits generalization to unfamiliar scenarios. Recent development of vision-language-action (VLA) models has presented an end-to-end approach for general robotic manipulation tasks. Although VLAs have demonstrated promising performance on simple tasks, the feasibility of applying such models to complex disassembly remains largely unexplored. In this paper, we collected a customized dataset for robotic RAM and CPU disassembly and used it to fine-tune two well-established VLA approaches, OpenVLA and OpenVLA-OFT, as a case study. We divided the whole disassembly task into several small steps, and our preliminary experimental results indicate that the fine-tuned VLA models can faithfully complete multiple early steps but struggle with certain critical subtasks, leading to task failure. However, we observed that a simple hybrid strategy that combines VLA with a rule-based controller can successfully perform the entire disassembly operation. These findings highlight the current limitations of VLA models in handling the dexterity and precision required for robotic EoL product disassembly. By offering a detailed analysis of the observed results, this study provides insights that may inform future research to address current challenges and advance end-to-end robotic automated disassembly. |
|
| MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Driving | 2025-12-04 | ShowEnd-to-End autonomous driving (E2E-AD) has emerged as a new paradigm, where trajectory planning plays a crucial role. Existing studies mainly follow two directions: trajectory generation oriented, which focuses on producing high-quality trajectories with simple decision mechanisms, and trajectory selection oriented, which performs multi-dimensional evaluation to select the best trajectory yet lacks sufficient generative capability. In this work, we propose MindDrive, a harmonized framework that integrates high-quality trajectory generation with comprehensive decision reasoning. It establishes a structured reasoning paradigm of "context simulation - candidate generation - multi-objective trade-off". In particular, the proposed Future-aware Trajectory Generator (FaTG), based on a World Action Model (WaM), performs ego-conditioned "what-if" simulations to predict potential future scenes and generate foresighted trajectory candidates. Building upon this, the VLM-oriented Evaluator (VLoE) leverages the reasoning capability of a large vision-language model to conduct multi-objective evaluations across safety, comfort, and efficiency dimensions, leading to reasoned and human-aligned decision making. Extensive experiments on the NAVSIM-v1 and NAVSIM-v2 benchmarks demonstrate that MindDrive achieves state-of-the-art performance across multi-dimensional driving metrics, significantly enhancing safety, compliance, and generalization. This work provides a promising path toward interpretable and cognitively guided autonomous driving. |
|
| FALCON: Actively Decoupled Visuomotor Policies for Loco-Manipulation with Foundation-Model-Based Coordination | 2025-12-04 | ShowWe present FoundAtion-model-guided decoupled LoCO-maNipulation visuomotor policies (FALCON), a framework for loco-manipulation that combines modular diffusion policies with a vision-language foundation model as the coordinator. Our approach explicitly decouples locomotion and manipulation into two specialized visuomotor policies, allowing each subsystem to rely on its own observations. This mitigates the performance degradation that arise when a single policy is forced to fuse heterogeneous, potentially mismatched observations from locomotion and manipulation. Our key innovation lies in restoring coordination between these two independent policies through a vision-language foundation model, which encodes global observations and language instructions into a shared latent embedding conditioning both diffusion policies. On top of this backbone, we introduce a phase-progress head that uses textual descriptions of task stages to infer discrete phase and continuous progress estimates without manual phase labels. To further structure the latent space, we incorporate a coordination-aware contrastive loss that explicitly encodes cross-subsystem compatibility between arm and base actions. We evaluate FALCON on two challenging loco-manipulation tasks requiring navigation, precise end-effector placement, and tight base-arm coordination. Results show that it surpasses centralized and decentralized baselines while exhibiting improved robustness and generalization to out-of-distribution scenarios. |
|
| Hierarchical Vision Language Action Model Using Success and Failure Demonstrations | 2025-12-03 | ShowPrior Vision-Language-Action (VLA) models are typically trained on teleoperated successful demonstrations, while discarding numerous failed attempts that occur naturally during data collection. However, these failures encode where and how policies can be fragile, information that can be exploited to improve robustness. We address this problem by leveraging mixed-quality datasets to learn failure-aware reasoning at planning time. We introduce VINE, a hierarchical vision-language-action model that separates high-level reasoning (System 2) from low-level control (System 1) under a hierarchical reinforcement learning formalism, making failures usable as a structured learning signal rather than noisy supervision. System 2 performs feasibility-guided tree search over a 2D scene-graph abstraction: it proposes subgoal transitions, predicts success probabilities from both successes and failures, and prunes brittle branches before execution, effectively casting plan evaluation as feasibility scoring. The selected subgoal sequence is then passed to System 1, which executes low-level actions without modifying the agent's core skills. Trained entirely from offline teleoperation data, VINE integrates negative experience directly into the decision loop. Across challenging manipulation tasks, this approach consistently improves success rates and robustness, demonstrating that failure data is an essential resource for converting the broad competence of VLAs into robust execution. |
https... |
| PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention | 2025-12-03 | ShowThe Vision-Language-Action (VLA) models have demonstrated remarkable performance on embodied tasks and shown promising potential for real-world applications. However, current VLAs still struggle to produce consistent and precise target-oriented actions, as they often generate redundant or unstable motions along trajectories, limiting their applicability in time-sensitive scenarios.In this work, we attribute these redundant actions to the spatially uniform perception field of existing VLAs, which causes them to be distracted by target-irrelevant objects, especially in complex environments.To address this issue, we propose an efficient PosA-VLA framework that anchors visual attention via pose-conditioned supervision, consistently guiding the model's perception toward task-relevant regions. The pose-conditioned anchor attention mechanism enables the model to better align instruction semantics with actionable visual cues, thereby improving action generation precision and efficiency. Moreover, our framework adopts a lightweight architecture and requires no auxiliary perception modules (e.g., segmentation or grounding networks), ensuring efficient inference. Extensive experiments verify that our method executes embodied tasks with precise and time-efficient behavior across diverse robotic manipulation benchmarks and shows robust generalization in a variety of challenging environments. |
|
| Diagnose, Correct, and Learn from Manipulation Failures via Visual Symbols | 2025-12-03 | ShowVision-Language-Action (VLA) models have recently achieved remarkable progress in robotic manipulation, yet they remain limited in failure diagnosis and learning from failures. Additionally, existing failure datasets are mostly generated programmatically in simulation, which limits their generalization to the real world. In light of these, we introduce ViFailback, a framework designed to diagnose robotic manipulation failures and provide both textual and visual correction guidance. Our framework utilizes explicit visual symbols to enhance annotation efficiency. We further release the ViFailback dataset, a large-scale collection of 58,126 Visual Question Answering (VQA) pairs along with their corresponding 5,202 real-world manipulation trajectories. Based on the dataset, we establish ViFailback-Bench, a benchmark of 11 fine-grained VQA tasks designed to assess the failure diagnosis and correction abilities of Vision-Language Models (VLMs), featuring ViFailback-Bench Lite for closed-ended and ViFailback-Bench Hard for open-ended evaluation. To demonstrate the effectiveness of our framework, we built the ViFailback-8B VLM, which not only achieves significant overall performance improvement on ViFailback-Bench but also generates visual symbols for corrective action guidance. Finally, by integrating ViFailback-8B with a VLA model, we conduct real-world robotic experiments demonstrating its ability to assist the VLA model in recovering from failures. Project Website: https://x1nyuzhou.github.io/vifailback.github.io/ |
|
| Towards Object-centric Understanding for Instructional Videos | 2025-12-03 | ShowUnderstanding procedural activities is crucial for developing future assistive AI that can reason about complex real-world tasks. Existing action-centric methods struggle with the flexibility of real procedures, where step order varies depending on object states. In this work, we propose to shift the focus to an object-centric paradigm by regarding actions as mechanisms that drive state transitions. To advance this direction, we introduce Object-IVQA, a long-form instructional video benchmark with 107 videos and 514 open-ended question-answer pairs annotated with temporally grounded evidence. The benchmark evaluates four dimensions of object-centric reasoning, including state evolution, precondition verification, counterfactual reasoning and mistake recognition. We further propose an agent framework that orchestrates object-centric planning, perception, analysis and generation tools, enabling explicit evidence retrieval and multi-hop reasoning across disjoint segments. Experiments show that existing large vision-language models struggle in object-level recognition and reasoning, whereas our framework achieves substantially improvement. |
|
| FPC-VLA: A Vision-Language-Action Framework with a Supervisor for Failure Prediction and Correction | 2025-12-03 | ShowRobotic manipulation is a fundamental component of automation. However, traditional perception-planning pipelines often fall short in open-ended tasks due to limited flexibility, while the architecture of a single end-to-end Vision-Language-Action (VLA) offers promising capabilities but lacks crucial mechanisms for anticipating and recovering from failure. To address these challenges, we propose FPC-VLA, a dual-model framework that integrates VLA with a supervisor for failure prediction and correction. The supervisor evaluates action viability through vision-language queries and generates corrective strategies when risks arise, trained efficiently without manual labeling. A dual-stream fusion module further refines actions by leveraging past predictions. Evaluation results on multiple simulation platforms (SIMPLER and LIBERO) and robot embodiments (WidowX, Google Robot, Franka) show that FPC-VLA outperforms state-of-the-art models in both zero-shot and fine-tuned settings. Successful real-world deployments on diverse, long-horizon tasks confirm FPC-VLA's strong generalization and practical utility for building more reliable autonomous systems. |
|
| Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos | 2025-12-02 | ShowDespite rapid advances in video generative models, robust metrics for evaluating visual and temporal correctness of complex human actions remain elusive. Critically, existing pure-vision encoders and Multimodal Large Language Models (MLLMs) are strongly appearance-biased, lack temporal understanding, and thus struggle to discern intricate motion dynamics and anatomical implausibilities in generated videos. We tackle this gap by introducing a novel evaluation metric derived from a learned latent space of real-world human actions. Our method first captures the nuances, constraints, and temporal smoothness of real-world motion by fusing appearance-agnostic human skeletal geometry features with appearance-based features. We posit that this combined feature space provides a robust representation of action plausibility. Given a generated video, our metric quantifies its action quality by measuring the distance between its underlying representations and this learned real-world action distribution. For rigorous validation, we develop a new multi-faceted benchmark specifically designed to probe temporally challenging aspects of human action fidelity. Through extensive experiments, we show that our metric achieves substantial improvement of more than 68% compared to existing state-of-the-art methods on our benchmark, performs competitively on established external benchmarks, and has a stronger correlation with human perception. Our in-depth analysis reveals critical limitations in current video generative models and establishes a new standard for advanced research in video generation. |
|
| VLA Models Are More Generalizable Than You Think: Revisiting Physical and Spatial Modeling | 2025-12-02 | ShowVision-language-action (VLA) models achieve strong in-distribution performance but degrade sharply under novel camera viewpoints and visual perturbations. We show that this brittleness primarily arises from misalignment in Spatial Modeling, rather than Physical Modeling. To address this, we propose a one-shot adaptation framework that recalibrates visual representations through lightweight, learnable updates. Our first method, Feature Token Modulation (FTM), applies a global affine transformation to visual tokens and improves Libero viewpoint accuracy from 48.5% to 87.1% with only 4K parameters. Building on this, Feature Linear Adaptation (FLA) introduces low-rank updates to the ViT encoder, achieving 90.8% success with 4.7M parameters -- matching LoRA-scale finetuning at far lower cost. Together, these results reveal substantial untapped robustness in pretrained VLA models and demonstrate that targeted, minimal visual adaptation is sufficient to restore viewpoint generalization. |
|
| GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation | 2025-12-02 | ShowWe present GR-RL, a robotic learning framework that turns a generalist vision-language-action (VLA) policy into a highly capable specialist for long-horizon dexterous manipulation. Assuming the optimality of human demonstrations is core to existing VLA policies. However, we claim that in highly dexterous and precise manipulation tasks, human demonstrations are noisy and suboptimal. GR-RL proposes a multi-stage training pipeline that filters, augments, and reinforces the demonstrations by reinforcement learning. First, GR-RL learns a vision-language-conditioned task progress, filters the demonstration trajectories, and only keeps the transitions that contribute positively to the progress. Specifically, we show that by directly applying offline RL with sparse reward, the resulting |
|
| Action Anticipation at a Glimpse: To What Extent Can Multimodal Cues Replace Video? | 2025-12-02 | ShowAnticipating actions before they occur is a core challenge in action understanding research. While conventional methods rely on extracting and aggregating temporal information from videos, as humans we can often predict upcoming actions by observing a single moment from a scene, when given sufficient context. Can a model achieve this competence? The short answer is yes, although its effectiveness depends on the complexity of the task. In this work, we investigate to what extent video aggregation can be replaced with alternative modalities. To this end, based on recent advances in visual feature extraction and language-based reasoning, we introduce AAG, a method for Action Anticipation at a Glimpse. AAG combines RGB features with depth cues from a single frame for enhanced spatial reasoning, and incorporates prior action information to provide long-term context. This context is obtained either through textual summaries from Vision-Language Models, or from predictions generated by a single-frame action recognizer. Our results demonstrate that multimodal single-frame action anticipation using AAG can perform competitively compared to both temporally aggregated video baselines and state-of-the-art methods across three instructional activity datasets: IKEA-ASM, Meccano, and Assembly101. |
Accep...Accepted in WACV 2026 - Applications Track |
| Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach | 2025-12-02 | ShowVision-Language-Action (VLA) models, trained via flow-matching or diffusion objectives, excel at learning complex behaviors from large-scale, multi-modal datasets (e.g., human teleoperation, scripted policies). However, since VLAs incorporate diverse data modes in the pre-training stage, and the finetuning dataset often contains demonstration data collected in a kinematically suboptimal or undesirable way, it exists redundant action modes that are irrelevant to the success action modes of the downstream task. Specifically, we observe a critical inference-time fragility among various sampled noises after supervised finetuning of pre-trained VLAs. In this paper, we attribute this instability to the distribution shift between the VLA policy and the policy induced by stable success modes of the downstream task dataset. Thus, we propose \textbf{TACO}, a test-time-scaling (TTS) framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks. The VLA models integrated with TACO can execute the actions with maximum pseudo-count from all sampled action chunks, thereby preventing distribution shifts while preserving the generalization ability of VLAs since the constraint is applied only during inference. Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits compared to RL update, especially for flow or diffusion-based VLAs which are difficult to perform RL update due to denoising process. Extensive experiments across four simulation benchmarks (RoboTwin2.0, Robotwin, LIBERO, SimplerEnv) and a dual-arm platform demonstrate that our method significantly improves the inference stability and success rates in downstream-task adaptations. |
The f...The first two authors contributed equally. Yang Zhang leads the whole project |
| Radiologist Copilot: An Agentic Assistant with Orchestrated Tools for Radiology Reporting with Quality Control | 2025-12-02 | ShowRadiology reporting is an essential yet time-consuming and error-prone task for radiologists in clinical examinations, especially for volumetric medical images. Rigorous quality control is also critical but tedious, ensuring that the final report meets clinical standards. Existing automated approaches, including radiology report generation methods and medical vision-language models, focus mainly on the report generation phase and neglect the crucial quality control procedure, limiting their capability to provide comprehensive support to radiologists. We propose Radiologist Copilot, an agentic AI assistant equipped with orchestrated tools designed for automated radiology reporting with quality control. Leveraging large language models as the reasoning backbone, the agentic system autonomously selects tools, plans, and executes actions, emulating the behavior of radiologists throughout the holistic radiology reporting process. The orchestrated tools include region localization, think with image paradigm directed region analysis planning, strategic template selection for report generation, quality assessment and feedback-driven adaptive refinement for quality control. Therefore, Radiologist Copilot facilitates accurate, complete, and efficient radiology reporting, assisting radiologists and improving clinical efficiency. Experimental results demonstrate that Radiologist Copilot significantly surpasses other state-of-the-art methods in radiology reporting. The source code will be released upon acceptance. |
|
| RoboWheel: A Data Engine from Real-World Human Demonstrations for Cross-Embodiment Robotic Learning | 2025-12-02 | ShowWe introduce Robowheel, a data engine that converts human hand object interaction (HOI) videos into training-ready supervision for cross morphology robotic learning. From monocular RGB or RGB-D inputs, we perform high precision HOI reconstruction and enforce physical plausibility via a reinforcement learning (RL) optimizer that refines hand object relative poses under contact and penetration constraints. The reconstructed, contact rich trajectories are then retargeted to cross-embodiments, robot arms with simple end effectors, dexterous hands, and humanoids, yielding executable actions and rollouts. To scale coverage, we build a simulation-augmented framework on Isaac Sim with diverse domain randomization (embodiments, trajectories, object retrieval, background textures, hand motion mirroring), which enriches the distributions of trajectories and observations while preserving spatial relationships and physical plausibility. The entire data pipeline forms an end to end pipeline from video,reconstruction,retargeting,augmentation data acquisition. We validate the data on mainstream vision language action (VLA) and imitation learning architectures, demonstrating that trajectories produced by our pipeline are as stable as those from teleoperation and yield comparable continual performance gains. To our knowledge, this provides the first quantitative evidence that HOI modalities can serve as effective supervision for robotic learning. Compared with teleoperation, Robowheel is lightweight, a single monocular RGB(D) camera is sufficient to extract a universal, embodiment agnostic motion representation that could be flexibly retargeted across embodiments. We further assemble a large scale multimodal dataset combining multi-camera captures, monocular videos, and public HOI corpora for training and evaluating embodied models. |
27 Pages, 21 figures |
| Learning Egocentric In-Hand Object Segmentation through Weak Supervision from Human Narrations | 2025-12-02 | ShowPixel-level recognition of objects manipulated by the user from egocentric images enables key applications spanning assistive technologies, industrial safety, and activity monitoring. However, progress in this area is currently hindered by the scarcity of annotated datasets, as existing approaches rely on costly manual labels. In this paper, we propose to learn human-object interaction detection leveraging narrations |
Under...Under consideration at Pattern Recognition Letters |
| AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention | 2025-12-02 | ShowVision-Language-Action (VLA) models have demonstrated remarkable capabilities in embodied AI tasks. However, existing VLA models, often built upon Vision-Language Models (VLMs), typically process dense visual inputs independently at each timestep. This approach implicitly models the task as a Markov Decision Process (MDP). However, this history-agnostic design is suboptimal for effective visual token processing in dynamic sequential decision-making, as it fails to leverage the context of history. To address this limitation, we reformulate the problem from a Partially Observable Markov Decision Process (POMDP) perspective and propose a novel framework named AVA-VLA. Inspired by the POMDP that the action generation should be conditioned on the belief state. AVA-VLA introduces Active Visual Attention (AVA) to dynamically modulate visual processing. It achieves this by leveraging the recurrent state, which is a neural approximation of the agent's belief state derived from the previous decision step. Specifically, the AVA module uses the recurrent state to compute the soft weights to actively process task-relevant visual tokens based on its historical context. Comprehensive evaluations demonstrate that AVA-VLA achieves state-of-the-art performance across popular robotic benchmarks, including LIBERO and CALVIN. Furthermore, real-world deployments on a dual-arm robot platform validate the framework's practical applicability and robust sim-to-real transferability. |
18 pages, 10 figures |
| Sigma: The Key for Vision-Language-Action Models toward Telepathic Alignment | 2025-12-02 | ShowTo address the gap in humanoid robot cognitive systems regarding the lack of a time-updable mediating thought space between semantics and continuous control, this study constructs and trains a VLA model named "Sigma" that runs on a single RTX 4090. It uses the open-source pi05_base model as a foundation and preprocesses svla_so101_pickplace into a training dataset. The researcher independently designed an architecture for a vision-language-action model that combines deep semantic understanding and association to achieve telepathic communication. The training process involved repeated optimizations of data preprocessing, LoRA fine-tuning, and the inference-stage adapter. The experiment employed offline closed-loop replay, comparing Sigma with the untuned pure pi05_base model under data conditions. Results showed that Sigma exhibited a stable decrease in control MSE across vector, fragment, and entire trajectory timescales, while maintaining the telepathy norm and semantic-text alignment quality unchanged. It demonstrates that mind-responsive alignment control is quantified through an architecture that combines deep understanding of semantics and association without retraining the base model, which provides reproducible experience for semantic alignment and intention-driven behavior in humanoid robots. |
The S...The Sigma model has been open-sourced on Hugging Face. Weights, dataset, some scripts, and logs are all available. The link is: https://huggingface.co/Veltraxor/Sigma |
| ManualVLA: A Unified VLA Model for Chain-of-Thought Manual Generation and Robotic Manipulation | 2025-12-01 | ShowVision-Language-Action (VLA) models have recently emerged, demonstrating strong generalization in robotic scene understanding and manipulation. However, when confronted with long-horizon tasks that require defined goal states, such as LEGO assembly or object rearrangement, existing VLA models still face challenges in coordinating high-level planning with precise manipulation. Therefore, we aim to endow a VLA model with the capability to infer the "how" process from the "what" outcomes, transforming goal states into executable procedures. In this paper, we introduce ManualVLA, a unified VLA framework built upon a Mixture-of-Transformers (MoT) architecture, enabling coherent collaboration between multimodal manual generation and action execution. Unlike prior VLA models that directly map sensory inputs to actions, we first equip ManualVLA with a planning expert that generates intermediate manuals consisting of images, position prompts, and textual instructions. Building upon these multimodal manuals, we design a Manual Chain-of-Thought (ManualCoT) reasoning process that feeds them into the action expert, where each manual step provides explicit control conditions, while its latent representation offers implicit guidance for accurate manipulation. To alleviate the burden of data collection, we develop a high-fidelity digital-twin toolkit based on 3D Gaussian Splatting, which automatically generates manual data for planning expert training. ManualVLA demonstrates strong real-world performance, achieving an average success rate 32% higher than the previous hierarchical SOTA baseline on LEGO assembly and object rearrangement tasks. |
|
| IGen: Scalable Data Generation for Robot Learning from Open-World Images | 2025-12-01 | ShowThe rise of generalist robotic policies has created an exponential demand for large-scale training data. However, on-robot data collection is labor-intensive and often limited to specific environments. In contrast, open-world images capture a vast diversity of real-world scenes that naturally align with robotic manipulation tasks, offering a promising avenue for low-cost, large-scale robot data acquisition. Despite this potential, the lack of associated robot actions hinders the practical use of open-world images for robot learning, leaving this rich visual resource largely unexploited. To bridge this gap, we propose IGen, a framework that scalably generates realistic visual observations and executable actions from open-world images. IGen first converts unstructured 2D pixels into structured 3D scene representations suitable for scene understanding and manipulation. It then leverages the reasoning capabilities of vision-language models to transform scene-specific task instructions into high-level plans and generate low-level actions as SE(3) end-effector pose sequences. From these poses, it synthesizes dynamic scene evolution and renders temporally coherent visual observations. Experiments validate the high quality of visuomotor data generated by IGen, and show that policies trained solely on IGen-synthesized data achieve performance comparable to those trained on real-world data. This highlights the potential of IGen to support scalable data generation from open-world images for generalist robotic policy training. |
8 pages, 8 figures |
| DiG-Flow: Discrepancy-Guided Flow Matching for Robust VLA Models | 2025-12-01 | ShowVision-Language-Action (VLA) models trained with flow matching have demonstrated impressive capabilities on robotic manipulation tasks. However, their performance often degrades under distribution shift and on complex multi-step tasks, suggesting that the learned representations may not robustly capture task-relevant semantics. We introduce DiG-Flow, a principled framework that enhances VLA robustness through geometric regularization. Our key insight is that the distributional discrepancy between observation and action embeddings provides a meaningful geometric signal: lower transport cost indicates compatible representations, while higher cost suggests potential misalignment. DiG-Flow computes a discrepancy measure between empirical distributions of observation and action embeddings, maps it to a modulation weight via a monotone function, and applies residual updates to the observation embeddings before flow matching. Crucially, this intervention operates at the representation level without modifying the flow matching path or target vector field. We provide theoretical guarantees showing that discrepancy-guided training provably decreases the training objective, and that guided inference refinement converges with contraction. Empirically, DiG-Flow integrates into existing VLA architectures with negligible overhead and consistently improves performance, with particularly pronounced gains on complex multi-step tasks and under limited training data. |
|
| RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Models | 2025-12-01 | ShowVision-Language-Action (VLA) models have recently emerged as powerful general-purpose policies for robotic manipulation, benefiting from large-scale multi-modal pre-training. However, they often fail to generalize reliably in out-of-distribution deployments, where unavoidable disturbances such as observation noise, sensor errors, or actuation perturbations become prevalent. While recent Reinforcement Learning (RL)-based post-training provides a practical means to adapt pre-trained VLA models, existing methods mainly emphasize reward maximization and overlook robustness to environmental uncertainty. In this work, we introduce RobustVLA, a lightweight online RL post-training method designed to explicitly enhance the resilience of VLA models. Through a systematic robustness analysis, we identify two key regularizations: Jacobian regularization, which mitigates sensitivity to observation noise, and smoothness regularization, which stabilizes policies under action perturbations. Extensive experiments across diverse robotic environments demonstrate that RobustVLA significantly outperforms prior state-of-the-art methods in robustness and reliability. Our results highlight the importance of principled robustness-aware RL post-training as a key step toward improving the reliability and robustness of VLA models. |
|
| NavForesee: A Unified Vision-Language World Model for Hierarchical Planning and Dual-Horizon Navigation Prediction | 2025-12-01 | ShowEmbodied navigation for long-horizon tasks, guided by complex natural language instructions, remains a formidable challenge in artificial intelligence. Existing agents often struggle with robust long-term planning about unseen environments, leading to high failure rates. To address these limitations, we introduce NavForesee, a novel Vision-Language Model (VLM) that unifies high-level language planning and predictive world model imagination within a single, unified framework. Our approach empowers a single VLM to concurrently perform planning and predictive foresight. Conditioned on the full instruction and historical observations, the model is trained to understand the navigation instructions by decomposing the task, tracking its progress, and formulating the subsequent sub-goal. Simultaneously, it functions as a generative world model, providing crucial foresight by predicting short-term environmental dynamics and long-term navigation milestones. The VLM's structured plan guides its targeted prediction, while the imagined future provides rich context to inform the navigation actions, creating a powerful internal feedback loop of perception-planning/prediction-action. We demonstrate through extensive experiments on the R2R-CE and RxR-CE benchmark that NavForesee achieves highly competitive performance in complex scenarios. Our work highlights the immense potential of fusing explicit language planning with implicit spatiotemporal prediction, paving the way for more intelligent and capable embodied agents. |
|
| AutoDrive-R$^2$: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving | 2025-12-01 | ShowVision-Language-Action (VLA) models in autonomous driving systems have recently demonstrated transformative potential by integrating multimodal perception with decision-making capabilities. However, the interpretability and coherence of the decision process and the plausibility of action sequences remain largely underexplored. To address these issues, we propose AutoDrive-R$^2$, a novel VLA framework that enhances both reasoning and self-reflection capabilities of autonomous driving systems through chain-of-thought (CoT) processing and reinforcement learning (RL). Specifically, we first propose an innovative CoT dataset named nuScenesR$^2$-6K for supervised fine-tuning, which effectively builds cognitive bridges between input information and output trajectories through a four-step logical chain with self-reflection for validation. Moreover, to maximize both reasoning and self-reflection during the RL stage, we further employ the Group Relative Policy Optimization (GRPO) algorithm within a physics-grounded reward framework that incorporates spatial alignment, vehicle dynamic, and temporal smoothness criteria to ensure reliable and realistic trajectory planning. Extensive evaluation results across both nuScenes and Waymo datasets demonstrates the state-of-the-art performance and robust generalization capacity of our proposed method. |
|
| VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference | 2025-11-30 | ShowVision-Language-Action models (VLAs) are becoming increasingly capable across diverse robotic tasks. However, their real-world deployment remains slow and inefficient: demonstration videos are often sped up by 5-10x to appear smooth, with noticeable action stalls and delayed reactions to environmental changes. Asynchronous inference offers a promising solution to achieve continuous and low-latency control by enabling robots to execute actions and perform inference simultaneously. However, because the robot and environment continue to evolve during inference, a temporal misalignment arises between the prediction and execution intervals. This leads to significant action instability, while existing methods either degrade accuracy or introduce runtime overhead to mitigate it. We propose VLASH, a general asynchronous inference framework for VLAs that delivers smooth, accurate, and fast reaction control without additional overhead or architectural changes. VLASH estimates the future execution-time state by rolling the robot state forward with the previously generated action chunk, thereby bridging the gap between prediction and execution. Experiments show that VLASH achieves up to 2.03x speedup and reduces reaction latency by up to 17.4x compared to synchronous inference while fully preserving the original accuracy. Moreover, it empowers VLAs to handle fast-reaction, high-precision tasks such as playing ping-pong and playing whack-a-mole, where traditional synchronous inference fails. Code is available at https://github.com/mit-han-lab/vlash |
|
| CycleManip: Enabling Cyclic Task Manipulation via Effective Historical Perception and Understanding | 2025-11-30 | ShowIn this paper, we explore an important yet underexplored task in robot manipulation: cycle-based manipulation, where robots need to perform cyclic or repetitive actions with an expected terminal time. These tasks are crucial in daily life, such as shaking a bottle or knocking a nail. However, few prior works have explored this task, leading to two main challenges: 1) the imitation methods often fail to complete these tasks within the expected terminal time due to the ineffective utilization of history; 2) the absence of a benchmark with sufficient data and automatic evaluation tools hinders development of effective solutions in this area. To address these challenges, we first propose the CycleManip framework to achieve cycle-based task manipulation in an end-to-end imitation manner without requiring any extra models, hierarchical structure or significant computational overhead. The core insight is to enhance effective history perception by a cost-aware sampling strategy and to improve historical understanding by multi-task learning. Second, we introduce a cycle-based task manipulation benchmark, which provides diverse cycle-based tasks, and an automatic evaluation method. Extensive experiments conducted in both simulation and real-world settings demonstrate that our method achieves high success rates in cycle-based task manipulation. The results further show strong adaptability performance in general manipulation, and the plug-and-play ability on imitation policies such as Vision-Language-Action (VLA) models. Moreover, the results show that our approach can be applied across diverse robotic platforms, including bi-arm grippers, dexterous hands, and humanoid robots. |
Proje...Project page: https://isee-laboratory.github.io/OmniDexGrasp/ |
| MM-ACT: Learn from Multimodal Parallel Generation to Act | 2025-11-30 | ShowA generalist robotic policy needs both semantic understanding for task planning and the ability to interact with the environment through predictive capabilities. To tackle this, we present MM-ACT, a unified Vision-Language-Action (VLA) model that integrates text, image, and action in shared token space and performs generation across all three modalities. MM-ACT adopts a re-mask parallel decoding strategy for text and image generation, and employs a one-step parallel decoding strategy for action generation to improve efficiency. We introduce Context-Shared Multimodal Learning, a unified training paradigm that supervises generation in all three modalities from a shared context, enhancing action generation through cross-modal learning. Experiments were conducted on the LIBERO simulation and Franka real-robot setups as well as RoboTwin2.0 to assess in-domain and out-of-domain performances respectively. Our approach achieves a success rate of 96.3% on LIBERO, 72.0% across three tasks of real Franka, and 52.38% across eight bimanual tasks of RoboTwin2.0 with an additional gain of 9.25% from cross-modal learning. We release our codes, models and data at https://github.com/HHYHRHY/MM-ACT. |
17 pages |
| SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models | 2025-11-30 | ShowVision-Language-Action (VLA) models excel in robotic manipulation but are constrained by their heavy reliance on expert demonstrations, leading to demonstration bias and limiting performance. Reinforcement learning (RL) is a vital post-training strategy to overcome these limits, yet current VLA-RL methods, including group-based optimization approaches, are crippled by severe reward sparsity. Relying on binary success indicators wastes valuable information in failed trajectories, resulting in low training efficiency. To solve this, we propose Self-Referential Policy Optimization (SRPO), a novel VLA-RL framework. SRPO eliminates the need for external demonstrations or manual reward engineering by leveraging the model's own successful trajectories, generated within the current training batch, as a self-reference. This allows us to assign a progress-wise reward to failed attempts. A core innovation is the use of latent world representations to measure behavioral progress robustly. Instead of relying on raw pixels or requiring domain-specific fine-tuning, we utilize the compressed, transferable encodings from a world model's latent space. These representations naturally capture progress patterns across environments, enabling accurate, generalized trajectory comparison. Empirical evaluations on the LIBERO benchmark demonstrate SRPO's efficiency and effectiveness. Starting from a supervised baseline with 48.9% success, SRPO achieves a new state-of-the-art success rate of 99.2% in just 200 RL steps, representing a 103% relative improvement without any extra supervision. Furthermore, SRPO shows substantial robustness, achieving a 167% performance improvement on the LIBERO-Plus benchmark. |
|
| SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead | 2025-11-30 | ShowVision-Language-Action (VLA) models built on pretrained Vision-Language Models (VLMs) show strong potential but are limited in practicality due to their large parameter counts. To mitigate this issue, using a lightweight VLM has been explored, but it compromises spatiotemporal reasoning. Although some methods suggest that incorporating additional 3D inputs can help, they usually rely on large VLMs to fuse 3D and 2D inputs and still lack temporal understanding. Therefore, we propose SwiftVLA, an architecture that enhances a compact model with 4D understanding while preserving design efficiency. Specifically, our approach features a pretrained 4D visual geometry transformer with a temporal cache that extracts 4D features from 2D images. Then, to enhance the VLM's ability to exploit both 2D images and 4D features, we introduce Fusion Tokens, a set of learnable tokens trained with a future prediction objective to generate unified representations for action generation. Finally, we introduce a mask-and-reconstruct strategy that masks 4D inputs to the VLM and trains the VLA to reconstruct them, enabling the VLM to learn effective 4D representations and allowing the 4D branch to be dropped at inference with minimal performance loss. Experiments in real and simulated environments show that SwiftVLA outperforms lightweight baselines and rivals VLAs up to 7 times larger, achieving comparable performance on edge devices while being 18 times faster and reducing memory footprint by 12 times. |
|
| GigaWorld-0: World Models as Data Engine to Empower Embodied AI | 2025-11-30 | ShowWorld models are emerging as a foundational paradigm for scalable, data-efficient embodied AI. In this work, we present GigaWorld-0, a unified world model framework designed explicitly as a data engine for Vision-Language-Action (VLA) learning. GigaWorld-0 integrates two synergistic components: GigaWorld-0-Video, which leverages large-scale video generation to produce diverse, texture-rich, and temporally coherent embodied sequences under fine-grained control of appearance, camera viewpoint, and action semantics; and GigaWorld-0-3D, which combines 3D generative modeling, 3D Gaussian Splatting reconstruction, physically differentiable system identification, and executable motion planning to ensure geometric consistency and physical realism. Their joint optimization enables the scalable synthesis of embodied interaction data that is visually compelling, spatially coherent, physically plausible, and instruction-aligned. Training at scale is made feasible through our efficient GigaTrain framework, which exploits FP8-precision and sparse attention to drastically reduce memory and compute requirements. We conduct comprehensive evaluations showing that GigaWorld-0 generates high-quality, diverse, and controllable data across multiple dimensions. Critically, VLA model (e.g., GigaBrain-0) trained on GigaWorld-0-generated data achieve strong real-world performance, significantly improving generalization and task success on physical robots without any real-world interaction during training. |
Proje...Project Page: https://giga-world-0.github.io/ |
| AFRAgent : An Adaptive Feature Renormalization Based High Resolution Aware GUI agent | 2025-11-30 | ShowThere is a growing demand for mobile user interface (UI) automation, driven by its broad applications across industries. With the advent of visual language models (VLMs), GUI automation has progressed from generating text-based instructions for humans to autonomously executing tasks, thus optimizing automation workflows. Recent approaches leverage VLMs for this problem due to their ability to 1) process on-screen content directly, 2) remain independent of device-specific APIs by utilizing human actions (e.g., clicks, typing), and 3) apply real-world contextual knowledge for task understanding. However, these models often have trouble accurately identifying widgets and determining actions due to limited spatial information in vision encoder features. Additionally, top-performing models are often large, requiring extensive training and resulting in inference delays. In this work, we introduce AFRAgent, an instruct-BLIP-based multimodal architecture that achieves superior performance in GUI automation while being less than one-fourth the size of its nearest competitor. To enhance image embeddings in the large language model (LLM) pipeline, we propose an adaptive feature renormalization-based (a token-level affine transformation) technique that effectively enriches low-resolution image embeddings and fuses high-resolution details. We evaluate AFRAgent on Meta-GUI and AITW benchmarks, establishing a new state-of-the-art baseline for smartphone automation. |
Accep...Accepted at WACV 2026 Conference |
| Transforming Monolithic Foundation Models into Embodied Multi-Agent Architectures for Human-Robot Collaboration | 2025-11-30 | ShowFoundation models have become central to unifying perception and planning in robotics, yet real-world deployment exposes a mismatch between their monolithic assumption that a single model can handle all cognitive functions and the distributed, dynamic nature of practical service workflows. Vision-language models offer strong semantic understanding but lack embodiment-aware action capabilities while relying on hand-crafted skills. Vision-Language-Action policies enable reactive manipulation but remain brittle across embodiments, weak in geometric grounding, and devoid of proactive collaboration mechanisms. These limitations indicate that scaling a single model alone cannot deliver reliable autonomy for service robots operating in human-populated settings. To address this gap, we present InteractGen, an LLM-powered multi-agent framework that decomposes robot intelligence into specialized agents for continuous perception, dependency-aware planning, decision and verification, failure reflection, and dynamic human delegation, treating foundation models as regulated components within a closed-loop collective. Deployed on a heterogeneous robot team and evaluated in a three-month open-use study, InteractGen improves task success, adaptability, and human-robot collaboration, providing evidence that multi-agent orchestration offers a more feasible path toward socially grounded service autonomy than further scaling standalone models. |
21 pa...21 pages, 16 figures, 4 tables |
| When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models | 2025-11-30 | ShowVision-Language-Action (VLA) models are vulnerable to adversarial attacks, yet universal and transferable attacks remain underexplored, as most existing patches overfit to a single model and fail in black-box settings. To address this gap, we present a systematic study of universal, transferable adversarial patches against VLA-driven robots under unknown architectures, finetuned variants, and sim-to-real shifts. We introduce UPA-RFAS (Universal Patch Attack via Robust Feature, Attention, and Semantics), a unified framework that learns a single physical patch in a shared feature space while promoting cross-model transfer. UPA-RFAS combines (i) a feature-space objective with an |
|
| AutocleanEEG ICVision: Automated ICA Artifact Classification Using Vision-Language AI | 2025-11-28 | ShowWe introduce EEG Autoclean Vision Language AI (ICVision) a first-of-its-kind system that emulates expert-level EEG ICA component classification through AI-agent vision and natural language reasoning. Unlike conventional classifiers such as ICLabel, which rely on handcrafted features, ICVision directly interprets ICA dashboard visualizations topography, time series, power spectra, and ERP plots, using a multimodal large language model (GPT-4 Vision). This allows the AI to see and explain EEG components the way trained neurologists do, making it the first scientific implementation of AI-agent visual cognition in neurophysiology. ICVision classifies each component into one of six canonical categories (brain, eye, heart, muscle, channel noise, and other noise), returning both a confidence score and a human-like explanation. Evaluated on 3,168 ICA components from 124 EEG datasets, ICVision achieved k = 0.677 agreement with expert consensus, surpassing MNE ICLabel, while also preserving clinically relevant brain signals in ambiguous cases. Over 97% of its outputs were rated as interpretable and actionable by expert reviewers. As a core module of the open-source EEG Autoclean platform, ICVision signals a paradigm shift in scientific AI, where models do not just classify, but see, reason, and communicate. It opens the door to globally scalable, explainable, and reproducible EEG workflows, marking the emergence of AI agents capable of expert-level visual decision-making in brain science and beyond. |
6 pages, 8 figures |
| Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer | 2025-11-28 | ShowGeneral-purpose robots need a deep understanding of the physical world, advanced reasoning, and general and dexterous control. This report introduces the latest generation of the Gemini Robotics model family: Gemini Robotics 1.5, a multi-embodiment Vision-Language-Action (VLA) model, and Gemini Robotics-ER 1.5, a state-of-the-art Embodied Reasoning (ER) model. We are bringing together three major innovations. First, Gemini Robotics 1.5 features a novel architecture and a Motion Transfer (MT) mechanism, which enables it to learn from heterogeneous, multi-embodiment robot data and makes the VLA more general. Second, Gemini Robotics 1.5 interleaves actions with a multi-level internal reasoning process in natural language. This enables the robot to "think before acting" and notably improves its ability to decompose and execute complex, multi-step tasks, and also makes the robot's behavior more interpretable to the user. Third, Gemini Robotics-ER 1.5 establishes a new state-of-the-art for embodied reasoning, i.e., for reasoning capabilities that are critical for robots, such as visual and spatial understanding, task planning, and progress estimation. Together, this family of models takes us a step towards an era of physical agents-enabling robots to perceive, think and then act so they can solve complex multi-step tasks. |
|
| Adapting Like Humans: A Metacognitive Agent with Test-time Reasoning | 2025-11-28 | ShowRecent Vision-Language Models (VLMs) exhibit strong perceptual reasoning abilities, yet they often struggle to adapt efficiently when encountering novel tasks at test time. In contrast, humans leverage the metacognitive model with memory, enabling continuous strategy refinement through metacognitive control when faced with new challenges. To bridge this gap, we propose metacognitive test-time reasoning (MCTR), a framework that equips models with the ability to learn, adapt, and improve during test time through metacognitive self-updating. Inspired by the dual structure of human metacognition, MCTR comprises meta-level and object-level VLM reasoning modules, each equipped with dedicated memory systems for hierarchical adaptive reasoning. Specifically, MCTR consists of (1) a meta-reasoning module which incrementally builds a structured memory by discovering and storing task-relevant rules, environmental patterns, and action-outcome relationships from test-time observations as natural language descriptions; and (2) an action-reasoning module that determines optimal actions through context-aware perception and strategic reasoning by dynamically retrieving and integrating knowledge from memory. The action-reasoning module continuously updates its policy through proposed metacognitive test-time reinforcement learning, adapting as knowledge memory evolves. We evaluate MCTR on 45 Atari games (33 seen, 12 unseen). MCTR demonstrates robust test-time adaptation, achieving 9/12 top-1 results on unseen games compared with baselines. Analyses through ablations, learning dynamics, and case studies reveal the complementary contributions of both components and show meta-reasoning evolving toward human-like adaptation strategies. |
|
| Obstruction reasoning for robotic grasping | 2025-11-28 | ShowSuccessful robotic grasping in cluttered environments not only requires a model to visually ground a target object but also to reason about obstructions that must be cleared beforehand. While current vision-language embodied reasoning models show emergent spatial understanding, they remain limited in terms of obstruction reasoning and accessibility planning. To bridge this gap, we present UNOGrasp, a learning-based vision-language model capable of performing visually-grounded obstruction reasoning to infer the sequence of actions needed to unobstruct the path and grasp the target object. We devise a novel multi-step reasoning process based on obstruction paths originated by the target object. We anchor each reasoning step with obstruction-aware visual cues to incentivize reasoning capability. UNOGrasp combines supervised and reinforcement finetuning through verifiable reasoning rewards. Moreover, we construct UNOBench, a large-scale dataset for both training and benchmarking, based on MetaGraspNetV2, with over 100k obstruction paths annotated by humans with obstruction ratios, contact points, and natural-language instructions. Extensive experiments and real-robot evaluations show that UNOGrasp significantly improves obstruction reasoning and grasp success across both synthetic and real-world environments, outperforming generalist and proprietary alternatives. Project website: https://tev-fbk.github.io/UnoGrasp/. |
|
| MindPower: Enabling Theory-of-Mind Reasoning in VLM-based Embodied Agents | 2025-11-28 | ShowTheory of Mind (ToM) refers to the ability to infer others' mental states, such as beliefs, desires, and intentions. Current vision-language embodied agents lack ToM-based decision-making, and existing benchmarks focus solely on human mental states while ignoring the agent's own perspective, hindering coherent decision and action generation. To address this, we propose MindPower, a Robot-Centric framework integrating Perception, Mental Reasoning, Decision Making and Action. Given multimodal inputs, MindPower first perceives the environment and human states, then performs ToM Reasoning to model both self and others, and finally generates decisions and actions guided by inferred mental states. Furthermore, we introduce Mind-Reward, a novel optimization objective that encourages VLMs to produce consistent ToM Reasoning and behavior. Our model outperforms GPT-4o by 12.77% in decision making and 12.49% in action generation. |
|
| LatBot: Distilling Universal Latent Actions for Vision-Language-Action Models | 2025-11-28 | ShowLearning transferable latent actions from large-scale object manipulation videos can significantly enhance generalization in downstream robotics tasks, as such representations are agnostic to different robot embodiments. Existing approaches primarily rely on visual reconstruction objectives while neglecting physical priors, leading to sub-optimal performance in learning universal representations. To address these challenges, we propose a Universal Latent Action Learning framework that takes task instructions and multiple frames as inputs, and optimizes both future frame reconstruction and action sequence prediction. Unlike prior works, incorporating action predictions (e.g., gripper or hand trajectories and orientations) allows the model to capture richer physical priors such as real-world distances and orientations, thereby enabling seamless transferability to downstream tasks. We further decompose the latent actions into learnable motion and scene tokens to distinguish the robot's active movements from environmental changes, thus filtering out irrelevant dynamics. By distilling the learned latent actions into the latest VLA models, we achieve strong performance across both simulated (SIMPLER and LIBERO) and real-world robot settings. Notably, with only 10 real-world trajectories per task collected on a Franka robot, our approach successfully completes all five challenging tasks, demonstrating strong few-shot transferability in robotic manipulation. |
Proje...Project Page: https://mm-robot.github.io/distill_latent_action/ |
| From Illusion to Intention: Visual Rationale Learning for Vision-Language Reasoning | 2025-11-28 | ShowRecent advances in vision-language reasoning underscore the importance of thinking with images, where models actively ground their reasoning in visual evidence. Yet, prevailing frameworks treat visual actions as optional tools, boosting metrics but leaving reasoning ungrounded and crops ineffective. This gap gives rise to the illusion of thinking with images: models seem visually grounded but rely on context-agnostic actions that neither refine perception nor guide reasoning toward correct answers. We address this problem by reframing visual actions as core reasoning primitives rather than optional tools, which we term visual rationalization, the visual analogue of textual Chain-of-Thought. Building on this insight, we propose Visual Rationale Learning (ViRL), an end-to-end paradigm that grounds training in the visual rationale itself. ViRL integrates (1) Process Supervision with ground-truth rationales, (2) Objective Alignment via step-level reward shaping, and (3) Fine-Grained Credit Assignment to distinguish correct, redundant, and erroneous actions. By ensuring each action contributes meaningfully to the reasoning chain, ViRL enables models to "get the right answer for the right visual reason". Trained purely with end-to-end RL, ViRL achieves state-of-the-art results across benchmarks spanning perception, hallucination, and reasoning. This work establishes visual rationalization as a task-agnostic, process-grounded paradigm for building transparent, verifiable, and trustworthy vision-language models. |
19 pages, 15 figures |
| Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspective | 2025-11-28 | ShowAs embodied agents operate in increasingly complex environments, the ability to perceive, track, and reason about individual object instances over time becomes essential, especially in tasks requiring sequenced interactions with visually similar objects. In these non-Markovian settings, key decision cues are often hidden in object-specific histories rather than the current scene. Without persistent memory of prior interactions (what has been interacted with, where it has been, or how it has changed) visuomotor policies may fail, repeat past actions, or overlook completed ones. To surface this challenge, we introduce LIBERO-Mem, a non-Markovian task suite for stress-testing robotic manipulation under object-level partial observability. It combines short- and long-horizon object tracking with temporally sequenced subgoals, requiring reasoning beyond the current frame. However, vision-language-action (VLA) models often struggle in such settings, with token scaling quickly becoming intractable even for tasks spanning just a few hundred frames. We propose Embodied-SlotSSM, a slot-centric VLA framework built for temporal scalability. It maintains spatio-temporally consistent slot identities and leverages them through two mechanisms: (1) slot-state-space modeling for reconstructing short-term history, and (2) a relational encoder to align the input tokens with action decoding. Together, these components enable temporally grounded, context-aware action prediction. Experiments show Embodied-SlotSSM's baseline performance on LIBERO-Mem and general tasks, offering a scalable solution for non-Markovian reasoning in object-centric robotic policies. |
Accep...Accepted at AAAI 2026 |
| Distracted Robot: How Visual Clutter Undermine Robotic Manipulation | 2025-11-27 | ShowIn this work, we propose an evaluation protocol for examining the performance of robotic manipulation policies in cluttered scenes. Contrary to prior works, we approach evaluation from a psychophysical perspective, therefore we use a unified measure of clutter that accounts for environmental factors as well as the distractors quantity, characteristics, and arrangement. Using this measure, we systematically construct evaluation scenarios in both hyper-realistic simulation and real-world and conduct extensive experimentation on manipulation policies, in particular vision-language-action (VLA) models. Our experiments highlight the significant impact of scene clutter, lowering the performance of the policies, by as much as 34% and show that despite achieving similar average performance across the tasks, different VLA policies have unique vulnerabilities and a relatively low agreement on success scenarios. We further show that our clutter measure is an effective indicator of performance degradation and analyze the impact of distractors in terms of their quantity and occluding influence. At the end, we show that finetuning on enhanced data, although effective, does not equally remedy all negative impacts of clutter on performance. |
12 figures, 2 tables |
| Improving Robotic Manipulation Robustness via NICE Scene Surgery | 2025-11-27 | ShowLearning robust visuomotor policies for robotic manipulation remains a challenge in real-world settings, where visual distractors can significantly degrade performance and safety. In this work, we propose an effective and scalable framework, Naturalistic Inpainting for Context Enhancement (NICE). Our method minimizes out-of-distribution (OOD) gap in imitation learning by increasing visual diversity through construction of new experiences using existing demonstrations. By utilizing image generative frameworks and large language models, NICE performs three editing operations, object replacement, restyling, and removal of distracting (non-target) objects. These changes preserve spatial relationships without obstructing target objects and maintain action-label consistency. Unlike previous approaches, NICE requires no additional robot data collection, simulator access, or custom model training, making it readily applicable to existing robotic datasets. Using real-world scenes, we showcase the capability of our framework in producing photo-realistic scene enhancement. For downstream tasks, we use NICE data to finetune a vision-language model (VLM) for spatial affordance prediction and a vision-language-action (VLA) policy for object manipulation. Our evaluations show that NICE successfully minimizes OOD gaps, resulting in over 20% improvement in accuracy for affordance prediction in highly cluttered scenes. For manipulation tasks, success rate increases on average by 11% when testing in environments populated with distractors in different quantities. Furthermore, we show that our method improves visual robustness, lowering target confusion by 6%, and enhances safety by reducing collision rate by 7%. |
11 figures, 3 tables |
| Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations | 2025-11-27 | ShowVision-Language Action (VLAs) models promise to extend the remarkable success of vision-language models (VLMs) to robotics. Yet, unlike VLMs in the vision-language domain, VLAs for robotics require finetuning to contend with varying physical factors like robot embodiment, environment characteristics, and spatial relationships of each task. Existing fine-tuning methods lack specificity, adapting the same set of parameters regardless of a task's visual, linguistic, and physical characteristics. Inspired by functional specificity in neuroscience, we hypothesize that it is more effective to finetune sparse model representations specific to a given task. In this work, we introduce Robotic Steering, a finetuning approach grounded in mechanistic interpretability that leverages few-shot demonstrations to identify and selectively finetune task-specific attention heads aligned with the physical, visual, and linguistic requirements of robotic tasks. Through comprehensive on-robot evaluations with a Franka Emika robot arm, we demonstrate that Robotic Steering outperforms LoRA while achieving superior robustness under task variation, reduced computational cost, and enhanced interpretability for adapting VLAs to diverse robotic tasks. |
|
| ArtiBench and ArtiBrain: Benchmarking Generalizable Vision-Language Articulated Object Manipulation | 2025-11-27 | ShowInteractive articulated manipulation requires long-horizon, multi-step interactions with appliances while maintaining physical consistency. Existing vision-language and diffusion-based policies struggle to generalize across parts, instances, and categories. We first introduce ArtiBench, a five-level benchmark covering kitchen, storage, office, and tool environments. ArtiBench enables structured evaluation from cross-part and cross-instance variation to long-horizon multi-object tasks, revealing the core generalization challenges of articulated object manipulation. Building on this benchmark, we propose ArtiBrain, a modular framework that unifies high-level reasoning with adaptive low-level control. ArtiBrain uses a VLM-based Task Reasoner (GPT-4.1) to decompose and validate subgoals, and employs a Hybrid Controller that combines geometry-aware keyframe execution with affordance-guided diffusion for precise and interpretable manipulation. An Affordance Memory Bank continually accumulates successful execution episodes and propagates part-level actionable affordances to unseen articulated parts and configurations. Extensive experiments on ArtiBench show that our ArtiBrain significantly outperforms state-of-the-art multimodal and diffusion-based methods in robustness and generalization. Code and dataset will be released upon acceptance. |
|
| Beyond Success: Refining Elegant Robot Manipulation from Mixed-Quality Data via Just-in-Time Intervention | 2025-11-27 | ShowVision-Language-Action (VLA) models have enabled notable progress in general-purpose robotic manipulation, yet their learned policies often exhibit variable execution quality. We attribute this variability to the mixed-quality nature of human demonstrations, where the implicit principles that govern how actions should be carried out are only partially satisfied. To address this challenge, we introduce the LIBERO-Elegant benchmark with explicit criteria for evaluating execution quality. Using these criteria, we develop a decoupled refinement framework that improves execution quality without modifying or retraining the base VLA policy. We formalize Elegant Execution as the satisfaction of Implicit Task Constraints (ITCs) and train an Elegance Critic via offline Calibrated Q-Learning to estimate the expected quality of candidate actions. At inference time, a Just-in-Time Intervention (JITI) mechanism monitors critic confidence and intervenes only at decision-critical moments, providing selective, on-demand refinement. Experiments on LIBERO-Elegant and real-world manipulation tasks show that the learned Elegance Critic substantially improves execution quality, even on unseen tasks. The proposed model enables robotic control that values not only whether tasks succeed, but also how they are performed. |
|
| CoT4AD: A Vision-Language-Action Model with Explicit Chain-of-Thought Reasoning for Autonomous Driving | 2025-11-27 | ShowVision-Language-Action (VLA) models have recently attracted growing attention in end-to-end autonomous driving for their strong reasoning capabilities and rich world knowledge. However, existing VLAs often suffer from limited numerical reasoning ability and overly simplified input-output mappings, which hinder their performance in complex driving scenarios requiring step-by-step causal reasoning. To address these challenges, we propose CoT4AD, a novel VLA framework that introduces Chain-of-Thought (CoT) reasoning for autonomous driving to enhance both numerical and causal reasoning in Vision-Language Models (VLMs). CoT4AD integrates visual observations and language instructions to perform semantic reasoning, scene understanding, and trajectory planning. During training, it explicitly models a perception-question-prediction-action CoT to align the reasoning space with the action space across multiple driving tasks. During inference, it performs implicit CoT reasoning to enable consistent numerical reasoning and robust decision-making in dynamic environments. Extensive experiments on both real-world and simulated benchmarks, including nuScenes and Bench2Drive, demonstrate that CoT4AD achieves state-of-the-art performance in both open-loop and closed-loop evaluations. Code will be released upon paper acceptance. |
10 pages, 3 figures |
| MonoDream: Monocular Vision-Language Navigation with Panoramic Dreaming | 2025-11-27 | ShowVision-Language Navigation (VLN) tasks often leverage panoramic RGB and depth inputs to provide rich spatial cues for action planning, but these sensors can be costly or less accessible in real-world deployments. Recent approaches based on Vision-Language Action (VLA) models achieve strong results with monocular input, yet they still lag behind methods using panoramic RGB-D information. We present MonoDream, a lightweight VLA framework that enables monocular agents to learn a Unified Navigation Representation (UNR). This shared feature representation jointly aligns navigation-relevant visual semantics (e.g., global layout, depth, and future cues) and language-grounded action intent, enabling more reliable action prediction. MonoDream further introduces Latent Panoramic Dreaming (LPD) tasks to supervise the UNR, which train the model to predict latent features of panoramic RGB and depth observations at both current and future steps based on only monocular input. Experiments on multiple VLN benchmarks show that MonoDream consistently improves monocular navigation performance and significantly narrows the gap with panoramic-based agents. |
|
| Foundation Models in Autonomous Driving: A Survey on Scenario Generation and Scenario Analysis | 2025-11-27 | ShowFor autonomous vehicles, safe navigation in complex environments depends on handling a broad range of diverse and rare driving scenarios. Simulation- and scenario-based testing have emerged as key approaches to development and validation of autonomous driving systems. Traditional scenario generation relies on rule-based systems, knowledge-driven models, and data-driven synthesis, often producing limited diversity and unrealistic safety-critical cases. With the emergence of foundation models, which represent a new generation of pre-trained, general-purpose AI models, developers can process heterogeneous inputs (e.g., natural language, sensor data, HD maps, and control actions), enabling the synthesis and interpretation of complex driving scenarios. In this paper, we conduct a survey about the application of foundation models for scenario generation and scenario analysis in autonomous driving (as of May 2025). Our survey presents a unified taxonomy that includes large language models, vision-language models, multimodal large language models, diffusion models, and world models for the generation and analysis of autonomous driving scenarios. In addition, we review the methodologies, open-source datasets, simulation platforms, and benchmark challenges, and we examine the evaluation metrics tailored explicitly to scenario generation and analysis. Finally, the survey concludes by highlighting the open challenges and research questions, and outlining promising future research directions. All reviewed papers are listed in a continuously maintained repository, which contains supplementary materials and is available at https://github.com/TUM-AVS/FM-for-Scenario-Generation-Analysis. |
Revis...Revised manuscript with separate evaluation metrics table |
| DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Action | 2025-11-27 | ShowTo build a generalizable Vision-Language-Action (VLA) model with strong reasoning ability, a common strategy is to first train a specialist VLA on robot demonstrations to acquire reliable manipulation skills, and then incorporate mixed annotated robot data together with multimodal data to restore broader reasoning capabilities. However, we observe that the resulting reasoning VLA often suffers from degraded action performance compared to the specialist model before fine-tuning, a phenomenon we refer to as action degeneration. To address this issue, we propose DualVLA, which enhances action performance through carefully designed post-training while still preserving reasoning capability. We first introduce a dual-layer data pruning method that removes redundant embodied reasoning, preventing it from adversely influencing action learning. To further strengthen action generation, we design a dual-teacher adaptive distillation strategy that assigns different supervision signals to different data domains while maintaining reasoning ability. To fill the evaluation gap for generalist VLAs, we also propose VLA Score, which decouples VLA capability into reasoning, intention, action, and alignment dimensions for a more fine-grained assessment. Experiments show that DualVLA achieves an average success rate of 61.0 in SimplerEnv and an average score of 65.4 across eight competitive multimodal benchmarks, demonstrating a stronger balance between precise action execution and multimodal understanding. Project Website: https://costaliya.github.io/DualVLA/. |
|
| $π_\texttt{RL}$: Online RL Fine-tuning for Flow-based Vision-Language-Action Models | 2025-11-27 | ShowVision-Language-Action (VLA) models enable robots to understand and perform complex tasks from multimodal input. Although recent work explores using reinforcement learning (RL) to automate the laborious data collection process in scaling supervised fine-tuning (SFT), applying large-scale RL to flow-based VLAs (\eg, |
Prepr...Preprint, work in progress. 27 pages |
| Attention-Guided Patch-Wise Sparse Adversarial Attacks on Vision-Language-Action Models | 2025-11-26 | ShowIn recent years, Vision-Language-Action (VLA) models in embodied intelligence have developed rapidly. However, existing adversarial attack methods require costly end-to-end training and often generate noticeable perturbation patches. To address these limitations, we propose ADVLA, a framework that directly applies adversarial perturbations on features projected from the visual encoder into the textual feature space. ADVLA efficiently disrupts downstream action predictions under low-amplitude constraints, and attention guidance allows the perturbations to be both focused and sparse. We introduce three strategies that enhance sensitivity, enforce sparsity, and concentrate perturbations. Experiments demonstrate that under an |
|
| VacuumVLA: Boosting VLA Capabilities via a Unified Suction and Gripping Tool for Complex Robotic Manipulation | 2025-11-26 | ShowVision Language Action models have significantly advanced general purpose robotic manipulation by harnessing large scale pretrained vision and language representations. Among existing approaches, a majority of current VLA systems employ parallel two finger grippers as their default end effectors. However, such grippers face inherent limitations in handling certain real world tasks such as wiping glass surfaces or opening drawers without handles due to insufficient contact area or lack of adhesion. To overcome these challenges, we present a low cost, integrated hardware design that combines a mechanical two finger gripper with a vacuum suction unit, enabling dual mode manipulation within a single end effector. Our system supports flexible switching or synergistic use of both modalities, expanding the range of feasible tasks. We validate the efficiency and practicality of our design within two state of the art VLA frameworks: DexVLA and Pi0. Experimental results demonstrate that with the proposed hybrid end effector, robots can successfully perform multiple complex tasks that are infeasible for conventional two finger grippers alone. All hardware designs and controlling systems will be released. |
8 pages |
| $\mathcal{E}_0$: Enhancing Generalization and Fine-Grained Control in VLA Models via Continuized Discrete Diffusion | 2025-11-26 | ShowVision-Language-Action (VLA) models offer a unified framework for robotic manipulation by integrating visual perception, language understanding, and control generation. Yet existing VLA models still struggle to generalize across diverse tasks, scenes, and camera viewpoints, and often produce coarse or unstable actions. We introduce E0, a continuized discrete diffusion framework that formulates action generation as iterative denoising over quantized action tokens. Compared with continuous diffusion policies, E0 offers two key advantages: (1) discrete action tokens align naturally with the symbolic structure of pretrained VLM/VLA backbones, enabling stronger semantic conditioning; and 2. discrete diffusion matches the true quantized nature of real-world robot control-whose hardware constraints (e.g., encoder resolution, control frequency, actuation latency) inherently discretize continuous signals-and therefore benefits from a Bayes-optimal denoiser that models the correct discrete action distribution, leading to stronger generalization. Compared with discrete autoregressive and mask-based discrete diffusion models, E0 supports a significantly larger and finer-grained action vocabulary and avoids the distributional mismatch introduced by masking-based corruptions-yielding more accurate fine-grained action control. We further introduce a spherical viewpoint perturbation augmentation method to improve robustness to camera shifts without additional data. Experiments on LIBERO, VLABench, and ManiSkill show that E0 achieves state-of-the-art performance across 14 diverse environments, outperforming strong baselines by 10.7% on average. Real-world evaluation on a Franka arm confirms that E0 delivers precise, robust, and transferable manipulation, establishing discrete diffusion as a promising direction for generalizable VLA policy learning. |
|
| From Observation to Action: Latent Action-based Primitive Segmentation for VLA Pre-training in Industrial Settings | 2025-11-26 | ShowWe present a novel unsupervised framework to unlock vast unlabeled human demonstration data from continuous industrial video streams for Vision-Language-Action (VLA) model pre-training. Our method first trains a lightweight motion tokenizer to encode motion dynamics, then employs an unsupervised action segmenter leveraging a novel "Latent Action Energy" metric to discover and segment semantically coherent action primitives. The pipeline outputs both segmented video clips and their corresponding latent action sequences, providing structured data directly suitable for VLA pre-training. Evaluations on public benchmarks and a proprietary electric motor assembly dataset demonstrate effective segmentation of key tasks performed by humans at workstations. Further clustering and quantitative assessment via a Vision-Language Model confirm the semantic coherence of the discovered action primitives. To our knowledge, this is the first fully automated end-to-end system for extracting and organizing VLA pre-training data from unstructured industrial videos, offering a scalable solution for embodied AI integration in manufacturing. |
10 pages, 5 figures |
| Exploring Automated Recognition of Instructional Activity and Discourse from Multimodal Classroom Data | 2025-11-26 | ShowObservation of classroom interactions can provide concrete feedback to teachers, but current methods rely on manual annotation, which is resource-intensive and hard to scale. This work explores AI-driven analysis of classroom recordings, focusing on multimodal instructional activity and discourse recognition as a foundation for actionable feedback. Using a densely annotated dataset of 164 hours of video and 68 lesson transcripts, we design parallel, modality-specific pipelines. For video, we evaluate zero-shot multimodal LLMs, fine-tuned vision-language models, and self-supervised video transformers on 24 activity labels. For transcripts, we fine-tune a transformer-based classifier with contextualized inputs and compare it against prompting-based LLMs on 19 discourse labels. To handle class imbalance and multi-label complexity, we apply per-label thresholding, context windows, and imbalance-aware loss functions. The results show that fine-tuned models consistently outperform prompting-based approaches, achieving macro-F1 scores of 0.577 for video and 0.460 for transcripts. These results demonstrate the feasibility of automated classroom analysis and establish a foundation for scalable teacher feedback systems. |
This ...This article has been accepted for publication in the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2026 |
| OVOD-Agent: A Markov-Bandit Framework for Proactive Visual Reasoning and Self-Evolving Detection | 2025-11-26 | ShowOpen-Vocabulary Object Detection (OVOD) aims to enable detectors to generalize across categories by leveraging semantic information. Although existing methods are pretrained on large vision-language datasets, their inference is still limited to fixed category names, creating a gap between multimodal training and unimodal inference. Previous work has shown that improving textual representation can significantly enhance OVOD performance, indicating that the textual space is still underexplored. To this end, we propose OVOD-Agent, which transforms passive category matching into proactive visual reasoning and self-evolving detection. Inspired by the Chain-of-Thought (CoT) paradigm, OVOD-Agent extends the textual optimization process into an interpretable Visual-CoT with explicit actions. OVOD's lightweight nature makes LLM-based management unsuitable; instead, we model visual context transitions as a Weakly Markovian Decision Process (w-MDP) over eight state spaces, which naturally represents the agent's state, memory, and interaction dynamics. A Bandit module generates exploration signals under limited supervision, helping the agent focus on uncertain regions and adapt its detection policy. We further integrate Markov transition matrices with Bandit trajectories for self-supervised Reward Model (RM) optimization, forming a closed loop from Bandit exploration to RM learning. Experiments on COCO and LVIS show that OVOD-Agent provides consistent improvements across OVOD backbones, particularly on rare categories, confirming the effectiveness of the proposed framework. |
| Title | Date | Abstract | Comment |
|---|---|---|---|
| Training-Time Action Conditioning for Efficient Real-Time Chunking | 2025-12-05 | ShowReal-time chunking (RTC) enables vision-language-action models (VLAs) to generate smooth, reactive robot trajectories by asynchronously predicting action chunks and conditioning on previously committed actions via inference-time inpainting. However, this inpainting method introduces computational overhead that increases inference latency. In this work, we propose a simple alternative: simulating inference delay at training time and conditioning on action prefixes directly, eliminating any inference-time overhead. Our method requires no modifications to the model architecture or robot runtime, and can be implemented with only a few additional lines of code. In simulated experiments, we find that training-time RTC outperforms inference-time RTC at higher inference delays. In real-world experiments on box building and espresso making tasks with the |
|
| AQUA-Net: Adaptive Frequency Fusion and Illumination Aware Network for Underwater Image Enhancement | 2025-12-05 | ShowUnderwater images often suffer from severe color distortion, low contrast, and a hazy appearance due to wavelength-dependent light absorption and scattering. Simultaneously, existing deep learning models exhibit high computational complexity, which limits their practical deployment for real-time underwater applications. To address these challenges, this paper presents a novel underwater image enhancement model, called Adaptive Frequency Fusion and Illumination Aware Network (AQUA-Net). It integrates a residual encoder decoder with dual auxiliary branches, which operate in the frequency and illumination domains. The frequency fusion encoder enriches spatial representations with frequency cues from the Fourier domain and preserves fine textures and structural details. Inspired by Retinex, the illumination-aware decoder performs adaptive exposure correction through a learned illumination map that separates reflectance from lighting effects. This joint spatial, frequency, and illumination design enables the model to restore color balance, visual contrast, and perceptual realism under diverse underwater conditions. Additionally, we present a high-resolution, real-world underwater video-derived dataset from the Mediterranean Sea, which captures challenging deep-sea conditions with realistic visual degradations to enable robust evaluation and development of deep learning models. Extensive experiments on multiple benchmark datasets show that AQUA-Net performs on par with SOTA in both qualitative and quantitative evaluations while using less number of parameters. Ablation studies further confirm that the frequency and illumination branches provide complementary contributions that improve visibility and color representation. Overall, the proposed model shows strong generalization capability and robustness, and it provides an effective solution for real-world underwater imaging applications. |
|
| M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG | 2025-12-05 | ShowVision-language models (VLMs) have achieved strong performance in visual question answering (VQA), yet they remain constrained by static training data. Retrieval-Augmented Generation (RAG) mitigates this limitation by enabling access to up-to-date, culturally grounded, and multilingual information; however, multilingual multimodal RAG remains largely underexplored. We introduce M4-RAG, a massive-scale benchmark covering 42 languages and 56 regional dialects and registers, comprising over 80,000 culturally diverse image-question pairs for evaluating retrieval-augmented VQA across languages and modalities. To balance realism with reproducibility, we build a controlled retrieval environment containing millions of carefully curated multilingual documents relevant to the query domains, approximating real-world retrieval conditions while ensuring consistent experimentation. Our systematic evaluation reveals that although RAG consistently benefits smaller VLMs, it fails to scale to larger models and often even degrades their performance, exposing a critical mismatch between model size and current retrieval effectiveness. M4-RAG provides a foundation for advancing next-generation RAG systems capable of reasoning seamlessly across languages, modalities, and cultural contexts. |
Preprint |
| SIMPACT: Simulation-Enabled Action Planning using Vision-Language Models | 2025-12-05 | ShowVision-Language Models (VLMs) exhibit remarkable common-sense and semantic reasoning capabilities. However, they lack a grounded understanding of physical dynamics. This limitation arises from training VLMs on static internet-scale visual-language data that contain no causal interactions or action-conditioned changes. Consequently, it remains challenging to leverage VLMs for fine-grained robotic manipulation tasks that require physical understanding, reasoning, and corresponding action planning. To overcome this, we present SIMPACT, a test-time, SIMulation-enabled ACTion Planning framework that equips VLMs with physical reasoning through simulation-in-the-loop world modeling, without requiring any additional training. From a single RGB-D observation, SIMPACT efficiently constructs physics simulations, enabling the VLM to propose informed actions, observe simulated rollouts, and iteratively refine its reasoning. By integrating language reasoning with physics prediction, our simulation-enabled VLM can understand contact dynamics and action outcomes in a physically grounded way. Our method demonstrates state-of-the-art performance on five challenging, real-world rigid-body and deformable manipulation tasks that require fine-grained physical reasoning, outperforming existing general-purpose robotic manipulation models. Our results demonstrate that embedding physics understanding via efficient simulation into VLM reasoning at test time offers a promising path towards generalizable embodied intelligence. Project webpage can be found at https://simpact-bot.github.io |
|
| Impugan: Learning Conditional Generative Models for Robust Data Imputation | 2025-12-05 | ShowIncomplete data are common in real-world applications. Sensors fail, records are inconsistent, and datasets collected from different sources often differ in scale, sampling rate, and quality. These differences create missing values that make it difficult to combine data and build reliable models. Standard imputation methods such as regression models, expectation-maximization, and multiple imputation rely on strong assumptions about linearity and independence. These assumptions rarely hold for complex or heterogeneous data, which can lead to biased or over-smoothed estimates. We propose Impugan, a conditional Generative Adversarial Network (cGAN) for imputing missing values and integrating heterogeneous datasets. The model is trained on complete samples to learn how missing variables depend on observed ones. During inference, the generator reconstructs missing entries from available features, and the discriminator enforces realism by distinguishing true from imputed data. This adversarial process allows Impugan to capture nonlinear and multimodal relationships that conventional methods cannot represent. In experiments on benchmark datasets and a multi-source integration task, Impugan achieves up to 82% lower Earth Mover's Distance (EMD) and 70% lower mutual-information deviation (MI) compared to leading baselines. These results show that adversarially trained generative models provide a scalable and principled approach for imputing and merging incomplete, heterogeneous data. Our model is available at: github.com/zalishmahmud/impuganBigData2025 |
|
| Designing an Optimal Sensor Network via Minimizing Information Loss | 2025-12-05 | ShowOptimal experimental design is a classic topic in statistics, with many well-studied problems, applications, and solutions. The design problem we study is the placement of sensors to monitor spatiotemporal processes, explicitly accounting for the temporal dimension in our modeling and optimization. We observe that recent advancements in computational sciences often yield large datasets based on physics-based simulations, which are rarely leveraged in experimental design. We introduce a novel model-based sensor placement criterion, along with a highly-efficient optimization algorithm, which integrates physics-based simulations and Bayesian experimental design principles to identify sensor networks that "minimize information loss" from simulated data. Our technique relies on sparse variational inference and (separable) Gauss-Markov priors, and thus may adapt many techniques from Bayesian experimental design. We validate our method through a case study monitoring air temperature in Phoenix, Arizona, using state-of-the-art physics-based simulations. Our results show our framework to be superior to random or quasi-random sampling, particularly with a limited number of sensors. We conclude by discussing practical considerations and implications of our framework, including more complex modeling tools and real-world deployments. |
37 pa...37 pages, 15 figures. Accepted to Bayesian Analysis |
| Measuring the Effect of Background on Classification and Feature Importance in Deep Learning for AV Perception | 2025-12-05 | ShowCommon approaches to explainable AI (XAI) for deep learning focus on analyzing the importance of input features on the classification task in a given model: saliency methods like SHAP and GradCAM are used to measure the impact of spatial regions of the input image on the classification result. Combined with ground truth information about the location of the object in the input image (e.g., a binary mask), it is determined whether object pixels had a high impact on the classification result, or whether the classification focused on background pixels. The former is considered to be a sign of a healthy classifier, whereas the latter is assumed to suggest overfitting on spurious correlations. A major challenge, however, is that these intuitive interpretations are difficult to test quantitatively, and hence the output of such explanations lacks an explanation itself. One particular reason is that correlations in real-world data are difficult to avoid, and whether they are spurious or legitimate is debatable. Synthetic data in turn can facilitate to actively enable or disable correlations where desired but often lack a sufficient quantification of realism and stochastic properties. [...] Therefore, we systematically generate six synthetic datasets for the task of traffic sign recognition, which differ only in their degree of camera variation and background correlation [...] to quantify the isolated influence of background correlation, different levels of camera variation, and considered traffic sign shapes on the classification performance, as well as background feature importance. [...] Results include a quantification of when and how much background features gain importance to support the classification task based on changes in the training domain [...]. Download: synset.de/datasets/synset-signset-ger/background-effect |
8 pag...8 pages, 2 figures, 7 tables |
| Synset Signset Germany: a Synthetic Dataset for German Traffic Sign Recognition | 2025-12-05 | ShowIn this paper, we present a synthesis pipeline and dataset for training / testing data in the task of traffic sign recognition that combines the advantages of data-driven and analytical modeling: GAN-based texture generation enables data-driven dirt and wear artifacts, rendering unique and realistic traffic sign surfaces, while the analytical scene modulation achieves physically correct lighting and allows detailed parameterization. In particular, the latter opens up applications in the context of explainable AI (XAI) and robustness tests due to the possibility of evaluating the sensitivity to parameter changes, which we demonstrate with experiments. Our resulting synthetic traffic sign recognition dataset Synset Signset Germany contains a total of 105500 images of 211 different German traffic sign classes, including newly published (2020) and thus comparatively rare traffic signs. In addition to a mask and a segmentation image, we also provide extensive metadata including the stochastically selected environment and imaging effect parameters for each image. We evaluate the degree of realism of Synset Signset Germany on the real-world German Traffic Sign Recognition Benchmark (GTSRB) and in comparison to CATERED, a state-of-the-art synthetic traffic sign recognition dataset. |
8 pag...8 pages, 8 figures, 3 tables |
| On the Bayes Inconsistency of Disagreement Discrepancy Surrogates | 2025-12-05 | ShowDeep neural networks often fail when deployed in real-world contexts due to distribution shift, a critical barrier to building safe and reliable systems. An emerging approach to address this problem relies on \emph{disagreement discrepancy} -- a measure of how the disagreement between two models changes under a shifting distribution. The process of maximizing this measure has seen applications in bounding error under shifts, testing for harmful shifts, and training more robust models. However, this optimization involves the non-differentiable zero-one loss, necessitating the use of practical surrogate losses. We prove that existing surrogates for disagreement discrepancy are not Bayes consistent, revealing a fundamental flaw: maximizing these surrogates can fail to maximize the true disagreement discrepancy. To address this, we introduce new theoretical results providing both upper and lower bounds on the optimality gap for such surrogates. Guided by this theory, we propose a novel disagreement loss that, when paired with cross-entropy, yields a provably consistent surrogate for disagreement discrepancy. Empirical evaluations across diverse benchmarks demonstrate that our method provides more accurate and robust estimates of disagreement discrepancy than existing approaches, particularly under challenging adversarial conditions. |
37 pages, 7 figures |
| World Models That Know When They Don't Know: Controllable Video Generation with Calibrated Uncertainty | 2025-12-05 | ShowRecent advances in generative video models have led to significant breakthroughs in high-fidelity video synthesis, specifically in controllable video generation where the generated video is conditioned on text and action inputs, e.g., in instruction-guided video editing and world modeling in robotics. Despite these exceptional capabilities, controllable video models often hallucinate - generating future video frames that are misaligned with physical reality - which raises serious concerns in many tasks such as robot policy evaluation and planning. However, state-of-the-art video models lack the ability to assess and express their confidence, impeding hallucination mitigation. To rigorously address this challenge, we propose C3, an uncertainty quantification (UQ) method for training continuous-scale calibrated controllable video models for dense confidence estimation at the subpatch level, precisely localizing the uncertainty in each generated video frame. Our UQ method introduces three core innovations to empower video models to estimate their uncertainty. First, our method develops a novel framework that trains video models for correctness and calibration via strictly proper scoring rules. Second, we estimate the video model's uncertainty in latent space, avoiding training instability and prohibitive training costs associated with pixel-space approaches. Third, we map the dense latent-space uncertainty to interpretable pixel-level uncertainty in the RGB space for intuitive visualization, providing high-resolution uncertainty heatmaps that identify untrustworthy regions. Through extensive experiments on large-scale robot learning datasets (Bridge and DROID) and real-world evaluations, we demonstrate that our method not only provides calibrated uncertainty estimates within the training distribution, but also enables effective out-of-distribution detection. |
|
| From Text to Returns: Using Large Language Models for Mutual Fund Portfolio Optimization and Risk-Adjusted Allocation | 2025-12-05 | ShowGenerative AI (GenAI) has enormous potential for improving two critical areas in investing, namely portfolio optimization (choosing the best combination of assets) and risk management (protecting those investments). Our study works at this intersection, using Large Language Models (LLMs) to upgrade how financial decisions are traditionally made. This research specifically tested how well advanced LLMs like Microsoft Phi 2, Mistral 7B, and Zypher 7B can create practical, risk-aware strategies for investing mutual funds in different sectors of the economy. Our method is sophisticated: it combines a Retrieval-Augmented Generation (RAG) pipeline, which enables the LLM to check external, real-time data with standard financial optimization methods. The model's advice is context-aware because we feed it large economic signals, like changes in the global economy. The Zypher 7B model was the clear winner. It consistently produced strategies that maximized investment returns while delivering better risk-adjusted results than the other models. Its ability to process complex relationships and contextual information makes it a highly powerful tool for financial allocation. In conclusion, our findings show that GenAI substantially improves performance over basic allocation methods. By connecting GenAI to real-world financial applications, this work lays the groundwork for creating smarter, more efficient, and more adaptable solutions for asset management professionals. |
|
| NeuroMemFPP: A recurrent neural approach for memory-aware parameter estimation in fractional Poisson process | 2025-12-05 | ShowIn this paper, we propose a recurrent neural network (RNN)-based framework for estimating the parameters of the fractional Poisson process (FPP), which models event arrivals with memory and long-range dependence. The Long Short-Term Memory (LSTM) network estimates the key parameters |
12 pages |
| Variational Uncertainty Decomposition for In-Context Learning | 2025-12-05 | ShowAs large language models (LLMs) gain popularity in conducting prediction tasks in-context, understanding the sources of uncertainty in in-context learning becomes essential to ensuring reliability. The recent hypothesis of in-context learning performing predictive Bayesian inference opens the avenue for Bayesian uncertainty estimation, particularly for decomposing uncertainty into epistemic uncertainty due to lack of in-context data and aleatoric uncertainty inherent in the in-context prediction task. However, the decomposition idea remains under-explored due to the intractability of the latent parameter posterior from the underlying Bayesian model. In this work, we introduce a variational uncertainty decomposition framework for in-context learning without explicitly sampling from the latent parameter posterior, by optimising auxiliary queries as probes to obtain an upper bound to the aleatoric uncertainty of an LLM's in-context learning procedure, which also induces a lower bound to the epistemic uncertainty. Through experiments on synthetic and real-world tasks, we show quantitatively and qualitatively that the decomposed uncertainties obtained from our method exhibit desirable properties of epistemic and aleatoric uncertainty. |
Neurips Version |
| SPARTAN: A Sparse Transformer World Model Attending to What Matters | 2025-12-05 | ShowCapturing the interactions between entities in a structured way plays a central role in world models that flexibly adapt to changes in the environment. Recent works motivate the benefits of models that explicitly represent the structure of interactions and formulate the problem as discovering local causal structures. In this work, we demonstrate that reliably capturing these relationships in complex settings remains challenging. To remedy this shortcoming, we postulate that sparsity is a critical ingredient for the discovery of such local structures. To this end, we present the SPARse TrANsformer World model (SPARTAN), a Transformer-based world model that learns context-dependent interaction structures between entities in a scene. By applying sparsity regularisation on the attention patterns between object-factored tokens, SPARTAN learns sparse, context-dependent interaction graphs that accurately predict future object states. We further extend our model to adapt to sparse interventions with unknown targets in the dynamics of the environment. This results in a highly interpretable world model that can efficiently adapt to changes. Empirically, we evaluate SPARTAN against the current state-of-the-art in object-centric world models in observation-based environments and demonstrate that our model can learn local causal graphs that accurately reflect the underlying interactions between objects, achieving significantly improved few-shot adaptation to dynamics changes, as well as robustness against distractors. |
|
| Vague Knowledge: Information without Transitivity and Partitions | 2025-12-05 | ShowI relax the standard assumptions of transitivity and partition structure in economic models of information to formalize vague knowledge: non-transitive indistinguishability over states. I show that vague knowledge, while failing to partition the state space, remains informative by distinguishing some states from others. Moreover, it can only be faithfully expressed through vague communication with blurred boundaries. My results provide microfoundations for the prevalence of natural language communication and qualitative reasoning in the real world, where knowledge is often vague. |
|
| Probing the effectiveness of World Models for Spatial Reasoning through Test-time Scaling | 2025-12-05 | ShowVision-Language Models (VLMs) remain limited in spatial reasoning tasks that require multi-view understanding and embodied perspective shifts. Recent approaches such as MindJourney attempt to mitigate this gap through test-time scaling where a world model imagines action-conditioned trajectories and a heuristic verifier selects helpful views from such trajectories. In this work, we systematically examine how such test-time verifiers behave across benchmarks, uncovering both their promise and their pitfalls. Our uncertainty-based analyses show that MindJourney's verifier provides little meaningful calibration, and that random scoring often reduces answer entropy equally well, thus exposing systematic action biases and unreliable reward signals. To mitigate these, we introduce a Verification through Spatial Assertions (ViSA) framework that grounds the test-time reward in verifiable, frame-anchored micro-claims. This principled verifier consistently improves spatial reasoning on the SAT-Real benchmark and corrects trajectory-selection biases through more balanced exploratory behavior. However, on the challenging MMSI-Bench, none of the verifiers, including ours, achieve consistent scaling, suggesting that the current world models form an information bottleneck where imagined views fail to enrich fine-grained reasoning. Together, these findings chart the bad, good, and ugly aspects of test-time verification for world-model-based reasoning. Our code is available at https://github.com/chandar-lab/visa-for-mindjourney. |
Exten...Extended abstract at World Modeling Workshop 2026 |
| 3D Path Planning for Robot-assisted Vertebroplasty from Arbitrary Bi-plane X-ray via Differentiable Rendering | 2025-12-05 | ShowRobotic systems are transforming image-guided interventions by enhancing accuracy and minimizing radiation exposure. A significant challenge in robotic assistance lies in surgical path planning, which often relies on the registration of intraoperative 2D images with preoperative 3D CT scans. This requirement can be burdensome and costly, particularly in procedures like vertebroplasty, where preoperative CT scans are not routinely performed. To address this issue, we introduce a differentiable rendering-based framework for 3D transpedicular path planning utilizing bi-planar 2D X-rays. Our method integrates differentiable rendering with a vertebral atlas generated through a Statistical Shape Model (SSM) and employs a learned similarity loss to refine the SSM shape and pose dynamically, independent of fixed imaging geometries. We evaluated our framework in two stages: first, through vertebral reconstruction from orthogonal X-rays for benchmarking, and second, via clinician-in-the-loop path planning using arbitrary-view X-rays. Our results indicate that our method outperformed a normalized cross-correlation baseline in reconstruction metrics (DICE: 0.75 vs. 0.65) and achieved comparable performance to the state-of-the-art model ReVerteR (DICE: 0.77), while maintaining generalization to arbitrary views. Success rates for bipedicular planning reached 82% with synthetic data and 75% with cadaver data, exceeding the 66% and 31% rates of a 2D-to-3D baseline, respectively. In conclusion, our framework facilitates versatile, CT-free 3D path planning for robot-assisted vertebroplasty, effectively accommodating real-world imaging diversity without the need for preoperative CT scans. |
|
| ZQBA: Zero Query Black-box Adversarial Attack | 2025-12-05 | ShowCurrent black-box adversarial attacks either require multiple queries or diffusion models to produce adversarial samples that can impair the target model performance. However, these methods require training a surrogate loss or diffusion models to produce adversarial samples, which limits their applicability in real-world settings. Thus, we propose a Zero Query Black-box Adversarial (ZQBA) attack that exploits the representations of Deep Neural Networks (DNNs) to fool other networks. Instead of requiring thousands of queries to produce deceiving adversarial samples, we use the feature maps obtained from a DNN and add them to clean images to impair the classification of a target model. The results suggest that ZQBA can transfer the adversarial samples to different models and across various datasets, namely CIFAR and Tiny ImageNet. The experiments also show that ZQBA is more effective than state-of-the-art black-box attacks with a single query, while maintaining the imperceptibility of perturbations, evaluated both quantitatively (SSIM) and qualitatively, emphasizing the vulnerabilities of employing DNNs in real-world contexts. All the source code is available at https://github.com/Joana-Cabral/ZQBA. |
Accep...Accepted in ICAART 2026 Conference |
| Towards agent-based-model informed neural networks | 2025-12-05 | ShowIn this article, we present a framework for designing neural networks that remain consistent with the underlying principles of agent-based models. We begin by highlighting the limitations of standard neural differential equations in modeling complex systems, where physical invariants (like energy) are often absent but other constraints (like mass conservation, network locality, bounded rationality) must be enforced. To address this, we introduce Agent-Based-Model informed Neural Networks(ABM-NNs), which leverage restricted graph neural networks and hierarchical decomposition to learn interpretable, structure-preserving dynamics. We validate the framework across three case studies of increasing complexity: (i) a generalized Generalized Lotka--Volterra system, where we recover ground-truth parameters from short trajectories in presence of interventions; (ii) a graph-based SIR contagion model, where our method outperforms state-of-the-art graph learning baselines (GCN, GraphSAGE, Graph Transformer) in out-of-sample forecasting and noise robustness; and (iii) a real-world macroeconomic model of the ten largest economies, where we learn coupled GDP dynamics from empirical data and demonstrate gradient-based counterfactual analysis for policy interventions. |
|
| QoSDiff: An Implicit Topological Embedding Learning Framework Leveraging Denoising Diffusion and Adversarial Attention for Robust QoS Prediction | 2025-12-05 | ShowAccurate Quality of Service (QoS) prediction is fundamental to service computing, providing essential data-driven guidance for service selection and ensuring superior user experiences. However, prevalent approaches, particularly Graph Neural Networks (GNNs), heavily rely on constructing explicit user--service interaction graphs. Such reliance not only leads to the intractability of explicit graph construction in large-scale scenarios but also limits the modeling of implicit topological relationships and exacerbates susceptibility to environmental noise and outliers. To address these challenges, this paper introduces \emph{QoSDiff}, a novel embedding learning framework that bypasses the prerequisite of explicit graph construction. Specifically, it leverages a denoising diffusion probabilistic model to recover intrinsic latent structures from noisy initializations. To further capture high-order interactions, we propose an adversarial interaction module that integrates a bidirectional hybrid attention mechanism. This adversarial paradigm dynamically distinguishes informative patterns from noise, enabling a dual-perspective modeling of intricate user--service associations. Extensive experiments on two large-scale real-world datasets demonstrate that QoSDiff significantly outperforms state-of-the-art baselines. Notably, the results highlight the framework's superior cross-dataset generalization capability and exceptional robustness against observational noise. |
Prepr...Preprint submitted to IEEE Transactions on Services Computing |
| From Correlation to Causation: Max-Pooling-Based Multi-Instance Learning Leads to More Robust Whole Slide Image Classification | 2025-12-05 | ShowIn whole slide images (WSIs) analysis, attention-based multi-instance learning (MIL) models are susceptible to spurious correlations and degrade under domain shift. These methods may assign high attention weights to non-tumor regions, such as staining biases or artifacts, leading to unreliable tumor region localization. In this paper, we revisit max-pooling-based MIL methods from a causal perspective. Under mild assumptions, our theoretical results demonstrate that max-pooling encourages the model to focus on causal factors while ignoring bias-related factors. Furthermore, we discover that existing max-pooling-based methods may overfit the training set through rote memorization of instance features and fail to learn meaningful patterns. To address these issues, we propose FocusMIL, which couples max-pooling with an instance-level variational information bottleneck (VIB) to learn compact, predictive latent representations, and employs a multi-bag mini-batch scheme to stabilize optimization. We conduct comprehensive experiments on three real-world datasets and one semi-synthetic dataset. The results show that, by capturing causal factors, FocusMIL exhibits significant advantages in out-of-distribution scenarios and instance-level tumor region localization tasks. |
|
| STATE-NAV: Stability-Aware Traversability Estimation for Bipedal Navigation on Rough Terrain | 2025-12-05 | ShowBipedal robots have advantages in maneuvering human-centered environments, but face greater failure risk compared to other stable mobile platforms such as wheeled or quadrupedal robots. While learning-based traversability has been widely studied for these platforms, bipedal traversability has instead relied on manually designed rules with limited consideration of locomotion stability on rough terrain. In this work, we present the first learning-based traversability estimation and risk-sensitive navigation framework for bipedal robots operating in diverse, uneven environments. TravFormer, a transformer-based neural network, is trained to predict bipedal instability with uncertainty, enabling risk-aware and adaptive planning. Based on the network, we define traversability as stability-aware command velocity-the fastest command velocity that keeps instability below a user-defined limit. This velocity-based traversability is integrated into a hierarchical planner that combines traversability-informed Rapid Random Tree Star (TravRRT*) for time-efficient planning and Model Predictive Control (MPC) for safe execution. We validate our method in MuJoCo simulation and the real world, demonstrating improved navigation performance, with enhanced robustness and time efficiency across varying terrains compared to existing methods. |
Accep...Accepted to IEEE Robotics and Automation Letters (RA-L) |
| Actor-Critic Model Predictive Control: Differentiable Optimization meets Reinforcement Learning for Agile Flight | 2025-12-05 | ShowA key open challenge in agile quadrotor flight is how to combine the flexibility and task-level generality of model-free reinforcement learning (RL) with the structure and online replanning capabilities of model predictive control (MPC), aiming to leverage their complementary strengths in dynamic and uncertain environments. This paper provides an answer by introducing a new framework called Actor-Critic Model Predictive Control. The key idea is to embed a differentiable MPC within an actor-critic RL framework. This integration allows for short-term predictive optimization of control actions through MPC, while leveraging RL for end-to-end learning and exploration over longer horizons. Through various ablation studies, conducted in the context of agile quadrotor racing, we expose the benefits of the proposed approach: it achieves better out-of-distribution behaviour, better robustness to changes in the quadrotor's dynamics and improved sample efficiency. Additionally, we conduct an empirical analysis using a quadrotor platform that reveals a relationship between the critic's learned value function and the cost function of the differentiable MPC, providing a deeper understanding of the interplay between the critic's value and the MPC cost functions. Finally, we validate our method in a drone racing task on different tracks, in both simulation and the real world. Our method achieves the same superhuman performance as state-of-the-art model-free RL, showcasing speeds of up to 21 m/s. We show that the proposed architecture can achieve real-time control performance, learn complex behaviors via trial and error, and retain the predictive properties of the MPC to better handle out-of-distribution behavior. |
20 pa...20 pages, 13 figures, evolved paper |
| BERTO: an Adaptive BERT-based Network Time Series Predictor with Operator Preferences in Natural Language | 2025-12-05 | ShowWe introduce BERTO, a BERT-based framework for traffic prediction and energy optimization in cellular networks. Built on transformer architectures, BERTO delivers high prediction accuracy, while its Balancing Loss Function and prompt-based customization allow operators to adjust the trade-off between power savings and performance. Natural language prompts guide the model to manage underprediction and overprediction in accordance with the operator's intent. Experiments on real-world datasets show that BERTO improves upon existing models with a |
|
| HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policies | 2025-12-05 | ShowThe development of foundation models for embodied intelligence critically depends on access to large-scale, high-quality robot demonstration data. Recent approaches have sought to address this challenge by training on large collections of heterogeneous robotic datasets. However, unlike vision or language data, robotic demonstrations exhibit substantial heterogeneity across embodiments and action spaces as well as other prominent variations such as senor configurations and action control frequencies. The lack of explicit designs for handling such heterogeneity causes existing methods to struggle with integrating diverse factors, thereby limiting their generalization and leading to degraded performance when transferred to new settings. In this paper, we present HiMoE-VLA, a novel vision-language-action (VLA) framework tailored to effectively handle diverse robotic data with heterogeneity. Specifically, we introduce a Hierarchical Mixture-of-Experts (HiMoE) architecture for the action module which adaptively handles multiple sources of heterogeneity across layers and gradually abstracts them into shared knowledge representations. Through extensive experimentation with simulation benchmarks and real-world robotic platforms, HiMoE-VLA demonstrates a consistent performance boost over existing VLA baselines, achieving higher accuracy and robust generalization across diverse robots and action spaces. The code and models are publicly available at https://github.com/ZhiyingDu/HiMoE-VLA. |
|
| Scenario-aware Uncertainty Quantification for Trajectory Prediction with Statistical Guarantees | 2025-12-05 | ShowReliable uncertainty quantification in trajectory prediction is crucial for safety-critical autonomous driving systems, yet existing deep learning predictors lack uncertainty-aware frameworks adaptable to heterogeneous real-world scenarios. To bridge this gap, we propose a novel scenario-aware uncertainty quantification framework to provide the predicted trajectories with prediction intervals and reliability assessment. To begin with, predicted trajectories from the trained predictor and their ground truth are projected onto the map-derived reference routes within the Frenet coordinate system. We then employ CopulaCPTS as the conformal calibration method to generate temporal prediction intervals for distinct scenarios as the uncertainty measure. Building upon this, within the proposed trajectory reliability discriminator (TRD), mean error and calibrated confidence intervals are synergistically analyzed to establish reliability models for different scenarios. Subsequently, the risk-aware discriminator leverages a joint risk model that integrates longitudinal and lateral prediction intervals within the Frenet coordinate to identify critical points. This enables segmentation of trajectories into reliable and unreliable segments, holding the advantage of informing downstream planning modules with actionable reliability results. We evaluated our framework using the real-world nuPlan dataset, demonstrating its effectiveness in scenario-aware uncertainty quantification and reliability assessment across diverse driving contexts. |
|
| Empirical Decision Theory | 2025-12-05 | ShowAnalyzing decision problems under uncertainty commonly relies on idealizing assumptions about the describability of the world, with the most prominent examples being the closed world and the small world assumption. Most assumptions are operationalized by introducing states of the world, conditional on which the decision situation can be analyzed without any remaining uncertainty. Conversely, most classical decision-theoretic approaches are not applicable if the states of the world are inaccessible. We propose a decision model that retains the appeal and simplicity of the original theory, but completely overcomes the need to specify the states of the world explicitly. The main idea of our approach is to address decision problems in a radically empirical way: instead of specifying states and consequences prior to the decision analysis, we only assume a protocol of observed act--consequence pairs as model primitives. We show how optimality in such empirical decision problems can be addressed by using protocol-based empirical choice functions and discuss three approaches for deriving inferential guarantees: (I) consistent statistical estimation of choice sets, (II) consistent statistical testing of choice functions with robustness guarantees, and (III) direct inference for empirical choice functions using credal sets. We illustrate our theory with a proof-of-concept application comparing different prompting strategies in generative AI models. |
Chris...Christoph Jansen and Georg Schollmeyer contributed equally |
| ReSem3D: Refinable 3D Spatial Constraints via Fine-Grained Semantic Grounding for Generalizable Robotic Manipulation | 2025-12-05 | ShowSemantics-driven 3D spatial constraints align highlevel semantic representations with low-level action spaces, facilitating the unification of task understanding and execution in robotic manipulation. The synergistic reasoning of Multimodal Large Language Models (MLLMs) and Vision Foundation Models (VFMs) enables cross-modal 3D spatial constraint construction. Nevertheless, existing methods have three key limitations: (1) coarse semantic granularity in constraint modeling, (2) lack of real-time closed-loop planning, (3) compromised robustness in semantically diverse environments. To address these challenges, we propose ReSem3D, a unified manipulation framework for semantically diverse environments, leveraging the synergy between VFMs and MLLMs to achieve fine-grained visual grounding and dynamically constructs hierarchical 3D spatial constraints for real-time manipulation. Specifically, the framework is driven by hierarchical recursive reasoning in MLLMs, which interact with VFMs to automatically construct 3D spatial constraints from natural language instructions and RGB-D observations in two stages: part-level extraction and region-level refinement. Subsequently, these constraints are encoded as real-time optimization objectives in joint space, enabling reactive behavior to dynamic disturbances. Extensive simulation and real-world experiments are conducted in semantically rich household and sparse chemical lab environments. The results demonstrate that ReSem3D performs diverse manipulation tasks under zero-shot conditions, exhibiting strong adaptability and generalization. Code and videos are available at https://github.com/scy-v/ReSem3D and https://resem3d.github.io. |
12 pages,9 figures |
| Vision-centric Token Compression in Large Language Model | 2025-12-05 | ShowReal-world applications are stretching context windows to hundreds of thousand of tokens while Large Language Models (LLMs) swell from billions to trillions of parameters. This dual expansion send compute and memory costs skyrocketing, making token compression indispensable. We introduce Vision Centric Token Compression (Vist), a slow-fast compression framework that mirrors human reading: the fast path renders distant tokens into images, letting a frozen, lightweight vision encoder skim the low-salience context; the slow path feeds the proximal window into the LLM for fine-grained reasoning. A Probability-Informed Visual Enhancement (PVE) objective masks high-frequency tokens during training, steering the Resampler to concentrate on semantically rich regions-just as skilled reader gloss over function words. On eleven in-context learning benchmarks, Vist achieves the same accuracy with 2.3 times fewer tokens, cutting FLOPs by 16% and memory by 50%. This method delivers remarkable results, outperforming the strongest text encoder-based compression method CEPE by 7.6% on average over benchmarks like TriviaQA, NQ, PopQA, NLUI, and CLIN, setting a new standard for token efficiency in LLMs. The project is at https://github.com/CSU-JPG/VIST. |
NeurI...NeurIPS 2025 spotlight |
| ProPhy: Progressive Physical Alignment for Dynamic World Simulation | 2025-12-05 | ShowRecent advances in video generation have shown remarkable potential for constructing world simulators. However, current models still struggle to produce physically consistent results, particularly when handling large-scale or complex dynamics. This limitation arises primarily because existing approaches respond isotropically to physical prompts and neglect the fine-grained alignment between generated content and localized physical cues. To address these challenges, we propose ProPhy, a Progressive Physical Alignment Framework that enables explicit physics-aware conditioning and anisotropic generation. ProPhy employs a two-stage Mixture-of-Physics-Experts (MoPE) mechanism for discriminative physical prior extraction, where Semantic Experts infer semantic-level physical principles from textual descriptions, and Refinement Experts capture token-level physical dynamics. This mechanism allows the model to learn fine-grained, physics-aware video representations that better reflect underlying physical laws. Furthermore, we introduce a physical alignment strategy that transfers the physical reasoning capabilities of vision-language models (VLMs) into the Refinement Experts, facilitating a more accurate representation of dynamic physical phenomena. Extensive experiments on physics-aware video generation benchmarks demonstrate that ProPhy produces more realistic, dynamic, and physically coherent results than existing state-of-the-art methods. |
|
| ToolMind Technical Report: A Large-Scale, Reasoning-Enhanced Tool-Use Dataset | 2025-12-05 | ShowLarge Language Model (LLM) agents have developed rapidly in recent years to solve complex real-world problems using external tools. However, the scarcity of high-quality trajectories still hinders the development of stronger LLM agents. Most existing works on multi-turn dialogue synthesis validate correctness only at the trajectory level, which may overlook turn-level errors that can propagate during training and degrade model performance. To address these limitations, we introduce ToolMind, a large-scale, high-quality tool-agentic dataset with 160k synthetic data instances generated using over 20k tools and 200k augmented open-source data instances. Our data synthesis pipeline first constructs a function graph based on parameter correlations and then uses a multi-agent framework to simulate realistic user-assistant-tool interactions. Beyond trajectory-level validation, we employ fine-grained turn-level filtering to remove erroneous or suboptimal steps, ensuring that only high-quality reasoning traces are retained. This approach mitigates error amplification during training while preserving self-corrective reasoning signals essential for robust tool-use learning. Models fine-tuned on ToolMind show significant improvements over baselines on several benchmarks. |
15 pages |
| HalluClean: A Unified Framework to Combat Hallucinations in LLMs | 2025-12-05 | ShowLarge language models (LLMs) have achieved impressive performance across a wide range of natural language processing tasks, yet they often produce hallucinated content that undermines factual reliability. To address this challenge, we introduce HalluClean, a lightweight and task-agnostic framework for detecting and correcting hallucinations in LLM-generated text. HalluClean adopts a reasoning-enhanced paradigm, explicitly decomposing the process into planning, execution, and revision stages to identify and refine unsupported claims. It employs minimal task-routing prompts to enable zero-shot generalization across diverse domains, without relying on external knowledge sources or supervised detectors. We conduct extensive evaluations on five representative tasks-question answering, dialogue, summarization, math word problems, and contradiction detection. Experimental results show that HalluClean significantly improves factual consistency and outperforms competitive baselines, demonstrating its potential to enhance the trustworthiness of LLM outputs in real-world applications. |
|
| Martian World Model: Controllable Video Synthesis with Physically Accurate 3D Reconstructions | 2025-12-05 | ShowSynthesizing realistic Martian landscape videos is crucial for mission rehearsal and robotic simulation. However, this task poses unique challenges due to the scarcity of high-quality Martian data and the significant domain gap between Martian and terrestrial imagery. To address these challenges, we propose a holistic solution composed of two key components: 1) A data curation pipeline Multimodal Mars Synthesis (M3arsSynth), which reconstructs 3D Martian environments from real stereo navigation images, sourced from NASA's Planetary Data System (PDS), and renders high-fidelity multiview 3D video sequences. 2) A Martian terrain video generator, MarsGen, which synthesizes novel videos visually realistic and geometrically consistent with the 3D structure encoded in the data. Our M3arsSynth engine spans a wide range of Martian terrains and acquisition dates, enabling the generation of physically accurate 3D surface models at metric-scale resolution. MarsGen, fine-tuned on M3arsSynth data, synthesizes videos conditioned on an initial image frame and, optionally, camera trajectories or textual prompts, allowing for video generation in novel environments. Experimental results show that our approach outperforms video synthesis models trained on terrestrial datasets, achieving superior visual fidelity and 3D structural consistency. |
Proje...Project Page: https://marsgenai.github.io |
| From Challenge to Change: Design Principles for AI Transformations | 2025-12-05 | ShowThe rapid rise of Artificial Intelligence (AI) is reshaping Software Engineering (SE), creating new opportunities while introducing human-centered challenges. Although prior work notes behavioral and other non-technical factors in AI integration, most studies still emphasize technical concerns and offer limited insight into how teams adapt to and trust AI. This paper proposes a Behavioral Software Engineering (BSE)-informed, human-centric framework to support SE organizations during early AI adoption. Using a mixed-methods approach, we built and refined the framework through a literature review of organizational change models and thematic analysis of interview data, producing concrete, actionable steps. The framework comprises nine dimensions: AI Strategy Design, AI Strategy Evaluation, Collaboration, Communication, Governance and Ethics, Leadership, Organizational Culture, Organizational Dynamics, and Up-skilling, each supported by design principles and actions. To gather preliminary practitioner input, we conducted a survey (N=105) and two expert workshops (N=4). Survey results show that Up-skilling (15.2%) and AI Strategy Design (15.1%) received the highest $100-method allocations, underscoring their perceived importance in early AI initiatives. Findings indicate that organizations currently prioritize procedural elements such as strategy design, while human-centered guardrails remain less developed. Workshop feedback reinforced these patterns and emphasized the need to ground the framework in real-world practice. By identifying key behavioral dimensions and offering actionable guidance, this work provides a pragmatic roadmap for navigating the socio-technical complexity of early AI adoption and highlights future research directions for human-centric AI in SE. |
Submitted to JSS |
| Decoding Selective Auditory Attention to Musical Elements in Ecologically Valid Music Listening | 2025-12-05 | ShowArt has long played a profound role in shaping human emotion, cognition, and behavior. While visual arts such as painting and architecture have been studied through eye tracking, revealing distinct gaze patterns between experts and novices, analogous methods for auditory art forms remain underdeveloped. Music, despite being a pervasive component of modern life and culture, still lacks objective tools to quantify listeners' attention and perceptual focus during natural listening experiences. To our knowledge, this is the first attempt to decode selective attention to musical elements using naturalistic, studio-produced songs and a lightweight consumer-grade EEG device with only four electrodes. By analyzing neural responses during real world like music listening, we test whether decoding is feasible under conditions that minimize participant burden and preserve the authenticity of the musical experience. Our contributions are fourfold: (i) decoding music attention in real studio-produced songs, (ii) demonstrating feasibility with a four-channel consumer EEG, (iii) providing insights for music attention decoding, and (iv) demonstrating improved model ability over prior work. Our findings suggest that musical attention can be decoded not only for novel songs but also across new subjects, showing performance improvements compared to existing approaches under our tested conditions. These findings show that consumer-grade devices can reliably capture signals, and that neural decoding in music could be feasible in real-world settings. This paves the way for applications in education, personalized music technologies, and therapeutic interventions. |
|
| FedIFL: A federated cross-domain diagnostic framework for motor-driven systems with inconsistent fault modes | 2025-12-05 | ShowDue to the scarcity of industrial data, individual equipment users, particularly start-ups, struggle to independently train a comprehensive fault diagnosis model; federated learning enables collaborative training while ensuring data privacy, making it an ideal solution. However, the diversity of working conditions leads to variations in fault modes, resulting in inconsistent label spaces across different clients. In federated diagnostic scenarios, label space inconsistency leads to local models focus on client-specific fault modes and causes local models from different clients to map different failure modes to similar feature representations, which weakens the aggregated global model's generalization. To tackle this issue, this article proposed a federated cross-domain diagnostic framework termed Federated Invariant Features Learning (FedIFL). In intra-client training, prototype contrastive learning mitigates intra-client domain shifts, subsequently, feature generating ensures local models can access distributions of other clients in a privacy-friendly manner. Besides, in cross-client training, a feature disentanglement mechanism is introduced to mitigate cross-client domain shifts, specifically, an instance-level federated instance consistency loss is designed to ensure the instance-level consistency of invariant features between different clients, furthermore, a federated instance personalization loss and an orthogonal loss are constructed to distinguish specific features that from the invariant features. Eventually, the aggregated model achieves promising generalization among global label spaces, enabling accurate fault diagnosis for target clients' Motor Driven Systems (MDSs) with inconsistent label spaces. Experiments on real-world MDSs validate the effectiveness and superiority of FedIFL in federated cross-domain diagnosis with inconsistent fault modes. |
Based...Based on reviewer feedback, we realized that the proposed FedIFL framework does not strictly conform to federated learning principles, since sharing primary features, label spaces and generator parameters with a central server may violate FL privacy requirements |
| Real-Time Execution of Action Chunking Flow Policies | 2025-12-05 | ShowModern AI systems, especially those interacting with the physical world, increasingly require real-time performance. However, the high latency of state-of-the-art generalist models, including recent vision-language action models (VLAs), poses a significant challenge. While action chunking has enabled temporal consistency in high-frequency control tasks, it does not fully address the latency problem, leading to pauses or out-of-distribution jerky movements at chunk boundaries. This paper presents a novel inference-time algorithm that enables smooth asynchronous execution of action chunking policies. Our method, real-time chunking (RTC), is applicable to any diffusion- or flow-based VLA out of the box with no re-training. It generates the next action chunk while executing the current one, "freezing" actions guaranteed to execute and "inpainting" the rest. To test RTC, we introduce a new benchmark of 12 highly dynamic tasks in the Kinetix simulator, as well as evaluate 6 challenging real-world bimanual manipulation tasks. Results demonstrate that RTC is fast, performant, and uniquely robust to inference delay, significantly improving task throughput and enabling high success rates in precise tasks |
publi...published in NeurIPS 2025 |
| Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment | 2025-12-05 | ShowVision-Language-Action (VLA) models have emerged as a powerful framework that unifies perception, language, and control, enabling robots to perform diverse tasks through multimodal understanding. However, current VLA models typically contain massive parameters and rely heavily on large-scale robot data pretraining, leading to high computational costs during training, as well as limited deployability for real-time inference. Moreover, most training paradigms often degrade the perceptual representations of the vision-language backbone, resulting in overfitting and poor generalization to downstream tasks. In this work, we present Evo-1, a lightweight VLA model that reduces computation and improves deployment efficiency, while maintaining strong performance without pretraining on robot data. Evo-1 builds on a native multimodal Vision-Language model (VLM), incorporating a novel cross-modulated diffusion transformer along with an optimized integration module, together forming an effective architecture. We further introduce a two-stage training paradigm that progressively aligns action with perception, preserving the representations of the VLM. Notably, with only 0.77 billion parameters, Evo-1 achieves state-of-the-art results on the Meta-World and RoboTwin suite, surpassing the previous best models by 12.4% and 6.9%, respectively, and also attains a competitive result of 94.8% on LIBERO. In real-world evaluations, Evo-1 attains a 78% success rate with high inference frequency and low memory overhead, outperforming all baseline methods. We release code, data, and model weights to facilitate future research on lightweight and efficient VLA models. |
Githu... |
| How Ensemble Learning Balances Accuracy and Overfitting: A Bias-Variance Perspective on Tabular Data | 2025-12-05 | ShowEnsemble models often achieve higher accuracy than single learners, but their ability to maintain small generalization gaps is not always well understood. This study examines how ensembles balance accuracy and overfitting across four tabular classification tasks: Breast Cancer, Heart Disease, Pima Diabetes, and Credit Card Fraud. Using repeated stratified cross validation with statistical significance testing, we compare linear models, a single decision tree, and nine ensemble methods. The results show that ensembles can reach high accuracy without large gaps by reducing variance through averaging or controlled boosting. On nearly linear and clean data, linear models already generalize well and ensembles offer little additional benefit. On datasets with meaningful nonlinear structure, tree based ensembles increase test accuracy by 5 to 7 points while keeping gaps below 3 percent. On noisy or highly imbalanced datasets, ensembles remain competitive but require regularization to avoid fitting noise or majority class patterns. We also compute simple dataset complexity indicators, such as linearity score, Fisher ratio, and noise estimate, which explain when ensembles are likely to control variance effectively. Overall, the study provides a clear view of how and when ensembles maintain high accuracy while keeping overfitting low, offering practical guidance for model selection in real world tabular applications. |
11 pa...11 pages, 9 figures, 3 tables. Code and reproducible experiments are available at: https://github.com/zubair0831/ensemble-generalization-gap |
| GTM: Simulating the World of Tools for AI Agents | 2025-12-05 | ShowThe integration of external tools is pivotal for empowering Large Language Model (LLM) agents with real-world capabilities. However, training these agents through direct, continuous interaction with diverse tools is often prohibitively expensive, slow, and introduces additional development and maintenance overhead. To address this challenge, we introduce the Generalist Tool Model (GTM), a 1.5-billion-parameter model that learns to act as a universal tool simulator. With only prompt-level configuration, GTM accesses tool functionalities along with input arguments and generates outputs that faithfully mimic real tool execution, providing a fast and cost-effective solution that eliminates development overhead. To build GTM, we propose the Context-Aware Response Generation (CARG) pipeline, which synthesizes comprehensive training data covering over 20,000 tools across 300 domains including physics, medicine, robotics, and finance. Through this pipeline, GTM learns to produce not only syntactically correct outputs but also logically coherent and contextually appropriate responses. Experiments demonstrate that GTM produces high-quality outputs with strong consistency and reliability. Besides when used in real reinforcement learning scenarios for agent training, GTM exhibits significantly faster simulation speed compared to real tools while maintaining comparable output quality, along with remarkable generalization and domain adaptability. Our results establish GTM as a foundational component for developing future AI agents, enabling efficient and scalable training of tool-augmented systems. |
|
| H-GAR: A Hierarchical Interaction Framework via Goal-Driven Observation-Action Refinement for Robotic Manipulation | 2025-12-05 | ShowUnified video and action prediction models hold great potential for robotic manipulation, as future observations offer contextual cues for planning, while actions reveal how interactions shape the environment. However, most existing approaches treat observation and action generation in a monolithic and goal-agnostic manner, often leading to semantically misaligned predictions and incoherent behaviors. To this end, we propose H-GAR, a Hierarchical interaction framework via Goal-driven observation-Action Refinement.To anchor prediction to the task objective, H-GAR first produces a goal observation and a coarse action sketch that outline a high-level route toward the goal. To enable explicit interaction between observation and action under the guidance of the goal observation for more coherent decision-making, we devise two synergistic modules. (1) Goal-Conditioned Observation Synthesizer (GOS) synthesizes intermediate observations based on the coarse-grained actions and the predicted goal observation. (2) Interaction-Aware Action Refiner (IAAR) refines coarse actions into fine-grained, goal-consistent actions by leveraging feedback from the intermediate observations and a Historical Action Memory Bank that encodes prior actions to ensure temporal consistency. By integrating goal grounding with explicit action-observation interaction in a coarse-to-fine manner, H-GAR enables more accurate manipulation. Extensive experiments on both simulation and real-world robotic manipulation tasks demonstrate that H-GAR achieves state-of-the-art performance. |
Accep...Accepted to AAAI 2026 (Oral), Project Page: https://github.com/JiuTian-VL/H-GAR |
| TED-4DGS: Temporally Activated and Embedding-based Deformation for 4DGS Compression | 2025-12-05 | ShowBuilding on the success of 3D Gaussian Splatting (3DGS) in static 3D scene representation, its extension to dynamic scenes, commonly referred to as 4DGS or dynamic 3DGS, has attracted increasing attention. However, designing more compact and efficient deformation schemes together with rate-distortion-optimized compression strategies for dynamic 3DGS representations remains an underexplored area. Prior methods either rely on space-time 4DGS with overspecified, short-lived Gaussian primitives or on canonical 3DGS with deformation that lacks explicit temporal control. To address this, we present TED-4DGS, a temporally activated and embedding-based deformation scheme for rate-distortion-optimized 4DGS compression that unifies the strengths of both families. TED-4DGS is built on a sparse anchor-based 3DGS representation. Each canonical anchor is assigned learnable temporal-activation parameters to specify its appearance and disappearance transitions over time, while a lightweight per-anchor temporal embedding queries a shared deformation bank to produce anchor-specific deformation. For rate-distortion compression, we incorporate an implicit neural representation (INR)-based hyperprior to model anchor attribute distributions, along with a channel-wise autoregressive model to capture intra-anchor correlations. With these novel elements, our scheme achieves state-of-the-art rate-distortion performance on several real-world datasets. To the best of our knowledge, this work represents one of the first attempts to pursue a rate-distortion-optimized compression framework for dynamic 3DGS representations. |
|
| Bita: A Conversational Assistant for Fairness Testing | 2025-12-05 | ShowBias in AI systems can lead to unfair and discriminatory outcomes, especially when left untested before deployment. Although fairness testing aims to identify and mitigate such bias, existing tools are often difficult to use, requiring advanced expertise and offering limited support for real-world workflows. To address this, we introduce Bita, a conversational assistant designed to help software testers detect potential sources of bias, evaluate test plans through a fairness lens, and generate fairness-oriented exploratory testing charters. Bita integrates a large language model with retrieval-augmented generation, grounding its responses in curated fairness literature. Our validation demonstrates how Bita supports fairness testing tasks on real-world AI systems, providing structured, reproducible evidence of its utility. In summary, our work contributes a practical tool that operationalizes fairness testing in a way that is accessible, systematic, and directly applicable to industrial practice. |
|
| LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference | 2025-12-05 | ShowKV cache has traditionally been stored in GPU memory to accelerate the decoding phase of large language model (LLM) inference. However, it is increasingly necessary to move KV caches outside GPU devices, to enable cache reuse across different queries and inference engines. Our real-world usage statistics confirm this trend: over time, the total KV cache stored by users has grown rapidly, far exceeding the capacity of GPU memory. Despite this need, there lacks an efficient solution for offloading and transferring KV caches. We present LMCACHE, the first and so far the most efficient open-source KV caching solution, which extracts and stores KV caches generated by modern LLM engines (vLLM and SGLang) out of the GPU memory and shares them across engines and queries. LMCACHE supports both cache offloading (prefix reuse across queries) and prefill-decode (PD) disaggregation (cross-engine/GPU cache transfer). LMCACHE's high performance and wide adoption stem from the following contributions: (1) highly optimized KV cache data movement powered by batched data movement operations, compute and I/O pipelining; (2) a modular KV cache connector component, decoupling LMCACHE from the rapid evolution of inference engines; (3) a first-class control API for flexible cache orchestration across GPU, CPU, storage, and network layers. Our evaluation shows that combining LMCACHE with vLLM achieves up to 15x improvement in throughput across workloads such as multi-round question answering and document analysis. Large-scale adoption of LMCACHE in enterprise settings provides us valuable insights, for example, fetching KV cache from remote storage has unsurprisingly benefits to prefill delay, and that context truncation, which is a widely applied technique in industry, can greatly reduce prefix cache hit ratio by half. The source code of LMCACHE is at: https://github.com/LMCache/LMCache. |
|
| Featurized-Decomposition Join: Low-Cost Semantic Joins with Guarantees | 2025-12-05 | ShowLarge Language Models (LLMs) are being increasingly used within data systems to process large datasets with text fields. A broad class of such tasks involves a semantic join-joining two tables based on a natural language predicate per pair of tuples, evaluated using an LLM. Semantic joins generalize tasks such as entity matching and record categorization, as well as more complex text understanding tasks. A naive implementation is expensive as it requires invoking an LLM for every pair of rows in the cross product. Existing approaches mitigate this cost by first applying embedding-based semantic similarity to filter candidate pairs, deferring to an LLM only when similarity scores are deemed inconclusive. However, these methods yield limited gains in practice, since semantic similarity may not reliably predict the join outcome. We propose Featurized-Decomposition Join (FDJ for short), a novel approach for performing semantic joins that significantly reduces cost while preserving quality. FDJ automatically extracts features and combines them into a logical expression in conjunctive normal form that we call a featurized decomposition to effectively prune out non-matching pairs. A featurized decomposition extracts key information from text records and performs inexpensive comparisons on the extracted features. We show how to use LLMs to automatically extract reliable features and compose them into logical expressions while providing statistical guarantees on the output result-an inherently challenging problem due to dependencies among features. Experiments on real-world datasets show up to 10 times reduction in cost compared with the state-of-the-art while providing the same quality guarantees. |
|
| The Dynamic Prior: Understanding 3D Structures for Casual Dynamic Videos | 2025-12-05 | ShowEstimating accurate camera poses, 3D scene geometry, and object motion from in-the-wild videos is a long-standing challenge for classical structure from motion pipelines due to the presence of dynamic objects. Recent learning-based methods attempt to overcome this challenge by training motion estimators to filter dynamic objects and focus on the static background. However, their performance is largely limited by the availability of large-scale motion segmentation datasets, resulting in inaccurate segmentation and, therefore, inferior structural 3D understanding. In this work, we introduce the Dynamic Prior (\ourmodel) to robustly identify dynamic objects without task-specific training, leveraging the powerful reasoning capabilities of Vision-Language Models (VLMs) and the fine-grained spatial segmentation capacity of SAM2. \ourmodel can be seamlessly integrated into state-of-the-art pipelines for camera pose optimization, depth reconstruction, and 4D trajectory estimation. Extensive experiments on both synthetic and real-world videos demonstrate that \ourmodel not only achieves state-of-the-art performance on motion segmentation, but also significantly improves accuracy and robustness for structural 3D understanding. |
Code ...Code is available at https://github.com/wuzy2115/DYNAPO |
| SOAP: Enhancing Spatio-Temporal Relation and Motion Information Capturing for Few-Shot Action Recognition | 2025-12-05 | ShowHigh frame-rate (HFR) videos of action recognition improve fine-grained expression while reducing the spatio-temporal relation and motion information density. Thus, large amounts of video samples are continuously required for traditional data-driven training. However, samples are not always sufficient in real-world scenarios, promoting few-shot action recognition (FSAR) research. We observe that most recent FSAR works build spatio-temporal relation of video samples via temporal alignment after spatial feature extraction, cutting apart spatial and temporal features within samples. They also capture motion information via narrow perspectives between adjacent frames without considering density, leading to insufficient motion information capturing. Therefore, we propose a novel plug-and-play architecture for FSAR called Spatio-tempOral frAme tuPle enhancer (SOAP) in this paper. The model we designed with such architecture refers to SOAP-Net. Temporal connections between different feature channels and spatio-temporal relation of features are considered instead of simple feature extraction. Comprehensive motion information is also captured, using frame tuples with multiple frames containing more motion information than adjacent frames. Combining frame tuples of diverse frame counts further provides a broader perspective. SOAP-Net achieves new state-of-the-art performance across well-known benchmarks such as SthSthV2, Kinetics, UCF101, and HMDB51. Extensive empirical evaluations underscore the competitiveness, pluggability, generalization, and robustness of SOAP. The code is released at https://github.com/wenbohuang1002/SOAP. |
Accep...Accepted by ACM MM 2024 |
| A Scene-aware Models Adaptation Scheme for Cross-scene Online Inference on Mobile Devices | 2025-12-05 | ShowEmerging Artificial Intelligence of Things (AIoT) applications desire online prediction using deep neural network (DNN) models on mobile devices. However, due to the movement of devices, unfamiliar test samples constantly appear, significantly affecting the prediction accuracy of a pre-trained DNN. In addition, unstable network connection calls for local model inference. In this paper, we propose a light-weight scheme, called Anole, to cope with the local DNN model inference on mobile devices. The core idea of Anole is to first establish an army of compact DNN models, and then adaptively select the model fitting the current test sample best for online inference. The key is to automatically identify model-friendly scenes for training scene-specific DNN models. To this end, we design a weakly-supervised scene representation learning algorithm by combining both human heuristics and feature similarity in separating scenes. Moreover, we further train a model classifier to predict the best-fit scene-specific DNN model for each test sample. We implement Anole on different types of mobile devices and conduct extensive trace-driven and real-world experiments based on unmanned aerial vehicles (UAVs). The results demonstrate that Anole outwits the method of using a versatile large DNN in terms of prediction accuracy (4.5% higher), response time (33.1% faster) and power consumption (45.1% lower). |
This ...This version presents the extended and revised journal version of our 2024 conference paper, incorporating new datasets, expanded evaluations, and improved methodological details. The manuscript has been accepted for publication in IEEE Transactions on Mobile Computing |
| Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views | 2025-12-05 | ShowForecasting how human hands move in egocentric views is critical for applications like augmented reality and human-robot policy transfer. Recently, several hand trajectory prediction (HTP) methods have been developed to generate future possible hand waypoints, which still suffer from insufficient prediction targets, inherent modality gaps, entangled hand-head motion, and limited validation in downstream tasks. To address these limitations, we present a universal hand motion forecasting framework considering multi-modal input, multi-dimensional and multi-target prediction patterns, and multi-task affordances for downstream applications. We harmonize multiple modalities by vision-language fusion, global context incorporation, and task-aware text embedding injection, to forecast hand waypoints in both 2D and 3D spaces. A novel dual-branch diffusion is proposed to concurrently predict human head and hand movements, capturing their motion synergy in egocentric vision. By introducing target indicators, the prediction model can forecast the specific joint waypoints of the wrist or the fingers, besides the widely studied hand center points. In addition, we enable Uni-Hand to additionally predict hand-object interaction states (contact/separation) to facilitate downstream tasks better. As the first work to incorporate downstream task evaluation in the literature, we build novel benchmarks to assess the real-world applicability of hand motion forecasting algorithms. The experimental results on multiple publicly available datasets and our newly proposed benchmarks demonstrate that Uni-Hand achieves the state-of-the-art performance in multi-dimensional and multi-target hand motion forecasting. Extensive validation in multiple downstream tasks also presents its impressive human-robot policy transfer to enable robotic manipulation, and effective feature enhancement for action anticipation/recognition. |
Exten...Extended journal version of MMTwin (IROS'25). Code and data: https://github.com/IRMVLab/UniHand |
| TeleEgo: Benchmarking Egocentric AI Assistants in the Wild | 2025-12-05 | ShowEgocentric AI assistants in real-world settings must process multi-modal inputs (video, audio, text), respond in real time, and retain evolving long-term memory. However, existing benchmarks typically evaluate these abilities in isolation, lack realistic streaming scenarios, or support only short-term tasks. We introduce \textbf{TeleEgo}, a long-duration, streaming, omni-modal benchmark for evaluating egocentric AI assistants in realistic daily contexts. The dataset features over 14 hours per participant of synchronized egocentric video, audio, and text across four domains: work & study, lifestyle & routines, social activities, and outings & culture. All data is aligned on a unified global timeline and includes high-quality visual narrations and speech transcripts, curated through human refinement.TeleEgo defines 12 diagnostic subtasks across three core capabilities: Memory (recalling past events), Understanding (interpreting the current moment), and Cross-Memory Reasoning (linking distant events). It contains 3,291 human-verified QA items spanning multiple question formats (single-choice, binary, multi-choice, and open-ended), evaluated strictly in a streaming setting. We propose Real-Time Accuracy (RTA) to jointly capture correctness and responsiveness under tight decision windows, and Memory Persistence Time (MPT) as a forward-looking metric for long-term retention in continuous streams. In this work, we report RTA results for current models and release TeleEgo, together with an MPT evaluation framework, as a realistic and extensible benchmark for future egocentric assistants with stronger streaming memory, enabling systematic study of both real-time behavior and long-horizon memory. |
|
| FieldSeer I: Physics-Guided World Models for Long-Horizon Electromagnetic Dynamics under Partial Observability | 2025-12-05 | ShowWe introduce FieldSeer I, a geometry-aware world model that forecasts electromagnetic field dynamics from partial observations in 2-D TE waveguides. The model assimilates a short prefix of observed fields, conditions on a scalar source action and structure/material map, and generates closed-loop rollouts in the physical domain. Training in a symmetric-log domain ensures numerical stability. Evaluated on a reproducible FDTD benchmark (200 unique simulations, structure-wise split), FieldSeer I achieves higher suffix fidelity than GRU and deterministic baselines across three practical settings: (i) software-in-the-loop filtering (64x64, P=80->Q=80), (ii) offline single-file rollouts (80x140, P=240->Q=40), and (iii) offline multi-structure rollouts (80x140, P=180->Q=100). Crucially, it enables edit-after-prefix geometry modifications without re-assimilation. Results demonstrate that geometry-conditioned world models provide a practical path toward interactive digital twins for photonic design. |
|
| Conditional Generative Modeling for Enhanced Credit Risk Management in Supply Chain Finance | 2025-12-05 | ShowThe rapid expansion of cross-border e-commerce (CBEC) has created significant opportunities for small- and medium-sized sellers, yet financing remains a critical challenge due to their limited credit histories. Third-party logistics (3PL)-led supply chain finance (SCF) has emerged as a promising solution, leveraging in-transit inventory as collateral. We propose an advanced credit risk management framework tailored for 3PL-led SCF, addressing the dual challenges of credit risk assessment and loan size determination. Specifically, we leverage conditional generative modeling of sales distributions through Quantile-Regression-based Generative Metamodeling (QRGMM) as the foundation for risk measures estimation. We propose a unified framework that enables flexible estimation of multiple risk measures while introducing a functional risk measure formulation that systematically captures the relationship between these risk measures and varying loan levels, supported by theoretical guarantees. To capture complex covariate interactions in e-commerce sales data, we integrate QRGMM with Deep Factorization Machines (DeepFM). Extensive experiments on synthetic and real-world data validate the efficacy of our model for credit risk assessment and loan size determination. This study explores the use of generative models in CBEC SCF risk management, illustrating their potential to strengthen credit assessment and support financing for small- and medium-sized sellers. |
Accep...Accepted for publication in Naval Research Logistics (NRL) |
| Egyptian Ratscrew: Discovering Dominant Strategies with Computational Game Theory | 2025-12-05 | Show"Egyptian Ratscrew" (ERS) is a modern American card game enjoyed by millions of players worldwide. A game of ERS is won by collecting all of the cards in the deck. Typically this game is won by the player with the fastest reflexes, since the most common strategy for collecting cards is being the first to slap the pile in the center whenever legal combinations of cards are placed down. Most players assume that the dominant strategy is to develop a faster reaction time than your opponents, and no academic inquiry has been levied against this assumption. This thesis investigates the hypothesis that a "risk slapping" strategist who relies on practical economic decision making will win an overwhelming majority of games against players who rely on quick reflexes alone. It is theorized that this can be done by exploiting the "burn rule," a penalty that is too low-cost to effectively dissuade players from slapping illegally when it benefits them. Using the Ruby programming language, we construct an Egyptian Ratscrew simulator from scratch. Our model allows us to simulate the behavior of 8 strategically unique players within easily adjustable parameters including simulation type, player count, and burn amount. We simulate 100k iterations of 67 different ERS games, totaling 6.7 million games of ERS, and use win percentage data in order to determine which strategies are dominant under each set of parameters. We then confirm our hypothesis that risk slapping is a dominant strategy, discover that there is no strictly dominant approach to risk slapping, and elucidate a deeper understanding of different ERS mechanics such as the burn rule. Finally, we assess the implications of our findings and suggest potential improvements to the rules of the game. We also touch on the real-world applications of our research and make recommendations for the future of Egyptian Ratscrew modeling. |
21 pa...21 pages, 8 figures, link to source code available |
| Interval Regression: A Comparative Study with Proposed Models | 2025-12-04 | ShowRegression models are essential for a wide range of real-world applications. However, in practice, target values are not always precisely known; instead, they may be represented as intervals of acceptable values. This challenge has led to the development of Interval Regression models. In this study, we provide a comprehensive review of existing Interval Regression models and introduce alternative models for comparative analysis. Experiments are conducted on both real-world and synthetic datasets to offer a broad perspective on model performance. The results demonstrate that no single model is universally optimal, highlighting the importance of selecting the most suitable model for each specific scenario. |
13 pages, 4 figures |
| Seabed-to-Sky Mapping of Maritime Environments with a Dual Orthogonal SONAR and LiDAR Sensor Suite | 2025-12-04 | ShowCritical maritime infrastructure increasingly demands situational awareness both above and below the surface, yet existing ''seabed-to-sky'' mapping pipelines either rely on GNSS (vulnerable to shadowing/spoofing) or expensive bathymetric sonars. We present a unified, GNSS-independent mapping system that fuses LiDAR-IMU with a dual, orthogonally mounted Forward Looking Sonars (FLS) to generate consistent seabed-to-sky maps from an Autonomous Surface Vehicle. On the acoustic side, we extend orthogonal wide-aperture fusion to handle arbitrary inter-sonar translations (enabling heterogeneous, non-co-located models) and extract a leading edge from each FLS to form line-scans. On the mapping side, we modify LIO-SAM to ingest both stereo-derived 3D sonar points and leading-edge line-scans at and between keyframes via motion-interpolated poses, allowing sparse acoustic updates to contribute continuously to a single factor-graph map. We validate the system on real-world data from Belvederekanalen (Copenhagen), demonstrating real-time operation with approx. 2.65 Hz map updates and approx. 2.85 Hz odometry while producing a unified 3D model that spans air-water domains. |
|
| Beyond Detection: A Comprehensive Benchmark and Study on Representation Learning for Fine-Grained Webshell Family Classification | 2025-12-04 | ShowMalicious WebShells pose a significant and evolving threat by compromising critical digital infrastructures and endangering public services in sectors such as healthcare and finance. While the research community has made significant progress in WebShell detection (i.e., distinguishing malicious samples from benign ones), we argue that it is time to transition from passive detection to in-depth analysis and proactive defense. One promising direction is the automation of WebShell family classification, which involves identifying the specific malware lineage in order to understand an adversary's tactics and enable a precise, rapid response. This crucial task, however, remains a largely unexplored area that currently relies on slow, manual expert analysis. To address this gap, we present the first systematic study to automate WebShell family classification. Our method begins with extracting dynamic function call traces to capture inherent behaviors that are resistant to common encryption and obfuscation. To enhance the scale and diversity of our dataset for a more stable evaluation, we augment these real-world traces with new variants synthesized by Large Language Models. These augmented traces are then abstracted into sequences, graphs, and trees, providing a foundation to benchmark a comprehensive suite of representation methods. Our evaluation spans classic sequence-based embeddings (CBOW, GloVe), transformers (BERT, SimCSE), and a range of structure-aware algorithms, including Graph Kernels, Graph Edit Distance, Graph2Vec, and various Graph Neural Networks. Through extensive experiments on four real-world, family-annotated datasets under both supervised and unsupervised settings, we establish a robust baseline and provide practical insights into the most effective combinations of data abstractions, representation models, and learning paradigms for this challenge. |
|
| Inferring Compositional 4D Scenes without Ever Seeing One | 2025-12-04 | ShowScenes in the real world are often composed of several static and dynamic objects. Capturing their 4-dimensional structures, composition and spatio-temporal configuration in-the-wild, though extremely interesting, is equally hard. Therefore, existing works often focus on one object at a time, while relying on some category-specific parametric shape model for dynamic objects. This can lead to inconsistent scene configurations, in addition to being limited to the modeled object categories. We propose COM4D (Compositional 4D), a method that consistently and jointly predicts the structure and spatio-temporal configuration of 4D/3D objects using only static multi-object or dynamic single object supervision. We achieve this by a carefully designed training of spatial and temporal attentions on 2D video input. The training is disentangled into learning from object compositions on the one hand, and single object dynamics throughout the video on the other, thus completely avoiding reliance on 4D compositional training data. At inference time, our proposed attention mixing mechanism combines these independently learned attentions, without requiring any 4D composition examples. By alternating between spatial and temporal reasoning, COM4D reconstructs complete and persistent 4D scenes with multiple interacting objects directly from monocular videos. Furthermore, COM4D provides state-of-the-art results in existing separate problems of 4D object and composed 3D reconstruction despite being purely data-driven. |
Proje...Project page: https://github.com/insait-institute/COM4D |
| CARD: Correlation Aware Restoration with Diffusion | 2025-12-04 | ShowDenoising diffusion models have achieved state-of-the-art performance in image restoration by modeling the process as sequential denoising steps. However, most approaches assume independent and identically distributed (i.i.d.) Gaussian noise, while real-world sensors often exhibit spatially correlated noise due to readout mechanisms, limiting their practical effectiveness. We introduce Correlation Aware Restoration with Diffusion (CARD), a training-free extension of DDRM that explicitly handles correlated Gaussian noise. CARD first whitens the noisy observation, which converts the noise into an i.i.d. form. Then, the diffusion restoration steps are replaced with noise-whitened updates, which inherits DDRM's closed-form sampling efficiency while now being able to handle correlated noise. To emphasize the importance of addressing correlated noise, we contribute CIN-D, a novel correlated noise dataset captured across diverse illumination conditions to evaluate restoration methods on real rolling-shutter sensor noise. This dataset fills a critical gap in the literature for experimental evaluation with real-world correlated noise. Experiments on standard benchmarks with synthetic correlated noise and on CIN-D demonstrate that CARD consistently outperforms existing methods across denoising, deblurring, and super-resolution tasks. |
|
| Towards a Generalisable Cyber Defence Agent for Real-World Computer Networks | 2025-12-04 | ShowRecent advances in deep reinforcement learning for autonomous cyber defence have resulted in agents that can successfully defend simulated computer networks against cyber-attacks. However, many of these agents would need retraining to defend networks with differing topology or size, making them poorly suited to real-world networks where topology and size can vary over time. In this research we introduce a novel set of Topological Extensions for Reinforcement Learning Agents (TERLA) that provide generalisability for the defence of networks with differing topology and size, without the need for retraining. Our approach involves the use of heterogeneous graph neural network layers to produce a fixed-size latent embedding representing the observed network state. This representation learning stage is coupled with a reduced, fixed-size, semantically meaningful and interpretable action space. We apply TERLA to a standard deep reinforcement learning Proximal Policy Optimisation (PPO) agent model, and to reduce the sim-to-real gap, conduct our research using Cyber Autonomy Gym for Experimentation (CAGE) Challenge 4. This Cyber Operations Research Gym environment has many of the features of a real-world network, such as realistic Intrusion Detection System (IDS) events and multiple agents defending network segments of differing topology and size. TERLA agents retain the defensive performance of vanilla PPO agents whilst showing improved action efficiency. Generalisability has been demonstrated by showing that all TERLA agents have the same network-agnostic neural network architecture, and by deploying a single TERLA agent multiple times to defend network segments with differing topology and size, showing improved defensive performance and efficiency. |
Publi...Published in Proceedings of the 2025 Conference on Applied Machine Learning for Information Security: https://proceedings.mlr.press/v299/dudman25a.html |
| When unlearning is free: leveraging low influence points to reduce computational costs | 2025-12-04 | ShowAs concerns around data privacy in machine learning grow, the ability to unlearn, or remove, specific data points from trained models becomes increasingly important. While state of the art unlearning methods have emerged in response, they typically treat all points in the forget set equally. In this work, we challenge this approach by asking whether points that have a negligible impact on the model's learning need to be removed. Through a comparative analysis of influence functions across language and vision tasks, we identify subsets of training data with negligible impact on model outputs. Leveraging this insight, we propose an efficient unlearning framework that reduces the size of datasets before unlearning leading to significant computational savings (up to approximately 50 percent) on real world empirical examples. |
|
| Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model | 2025-12-04 | ShowRecovering pixel-wise geometric properties from a single image is fundamentally ill-posed due to appearance ambiguity and non-injective mappings between 2D observations and 3D structures. While discriminative regression models achieve strong performance through large-scale supervision, their success is bounded by the scale, quality and diversity of available data and limited physical reasoning. Recent diffusion models exhibit powerful world priors that encode geometry and semantics learned from massive image-text data, yet directly reusing their stochastic generative formulation is suboptimal for deterministic geometric inference: the former is optimized for diverse and high-fidelity image generation, whereas the latter requires stable and accurate predictions. In this work, we propose Lotus-2, a two-stage deterministic framework for stable, accurate and fine-grained geometric dense prediction, aiming to provide an optimal adaption protocol to fully exploit the pre-trained generative priors. Specifically, in the first stage, the core predictor employs a single-step deterministic formulation with a clean-data objective and a lightweight local continuity module (LCM) to generate globally coherent structures without grid artifacts. In the second stage, the detail sharpener performs a constrained multi-step rectified-flow refinement within the manifold defined by the core predictor, enhancing fine-grained geometry through noise-free deterministic flow matching. Using only 59K training samples, less than 1% of existing large-scale datasets, Lotus-2 establishes new state-of-the-art results in monocular depth estimation and highly competitive surface normal prediction. These results demonstrate that diffusion models can serve as deterministic world priors, enabling high-quality geometric reasoning beyond traditional discriminative and generative paradigms. |
Work ...Work done at the Hong Kong University of Science and Technology (Guangzhou). Project page: https://lotus-2.github.io/ |
| Learning to Code with Context: A Study-Based Approach | 2025-12-04 | ShowThe rapid emergence of generative AI tools is transforming the way software is developed. Consequently, software engineering education must adapt to ensure that students not only learn traditional development methods but also understand how to meaningfully and responsibly use these new technologies. In particular, project-based courses offer an effective environment to explore and evaluate the integration of AI assistance into real-world development practices. This paper presents our approach and a user study conducted within a university programming project in which students collaboratively developed computer games. The study investigates how participants used generative AI tools throughout different phases of the software development process, identifies the types of tasks where such tools were most effective, and analyzes the challenges students encountered. Building on these insights, we further examine a repository-aware, locally deployed large language model (LLM) assistant designed to provide project-contextualized support. The system employs Retrieval-Augmented Generation (RAG) to ground responses in relevant documentation and source code, enabling qualitative analysis of model behavior, parameter sensitivity, and common failure modes. The findings deepen our understanding of context-aware AI support in educational software projects and inform future integration of AI-based assistance into software engineering curricula. |
36 pa...36 pages, 7 figures, 5 tables |
| Bivariate Matrix-valued Linear Regression (BMLR): Finite-sample performance under Identifiability and Sparsity Assumptions | 2025-12-04 | ShowThis study explores the estimation of parameters in a matrix-valued linear regression model, where the |
36 pages, 8 figures |
| Variance Matters: Improving Domain Adaptation via Stratified Sampling | 2025-12-04 | ShowDomain shift remains a key challenge in deploying machine learning models to the real world. Unsupervised domain adaptation (UDA) aims to address this by minimising domain discrepancy during training, but the discrepancy estimates suffer from high variance in stochastic settings, which can stifle the theoretical benefits of the method. This paper proposes Variance-Reduced Domain Adaptation via Stratified Sampling (VaRDASS), the first specialised stochastic variance reduction technique for UDA. We consider two specific discrepancy measures -- correlation alignment and the maximum mean discrepancy (MMD) -- and derive ad hoc stratification objectives for these terms. We then present expected and worst-case error bounds, and prove that our proposed objective for the MMD is theoretically optimal (i.e., minimises the variance) under certain assumptions. Finally, a practical k-means style optimisation algorithm is introduced and analysed. Experiments on three domain shift datasets demonstrate improved discrepancy estimation accuracy and target domain performance. |
|
| AortaDiff: A Unified Multitask Diffusion Framework For Contrast-Free AAA Imaging | 2025-12-04 | ShowWhile contrast-enhanced CT (CECT) is standard for assessing abdominal aortic aneurysms (AAA), the required iodinated contrast agents pose significant risks, including nephrotoxicity, patient allergies, and environmental harm. To reduce contrast agent use, recent deep learning methods have focused on generating synthetic CECT from non-contrast CT (NCCT) scans. However, most adopt a multi-stage pipeline that first generates images and then performs segmentation, which leads to error accumulation and fails to leverage shared semantic and anatomical structures. To address this, we propose a unified deep learning framework that generates synthetic CECT images from NCCT scans while simultaneously segmenting the aortic lumen and thrombus. Our approach integrates conditional diffusion models (CDM) with multi-task learning, enabling end-to-end joint optimization of image synthesis and anatomical segmentation. Unlike previous multitask diffusion models, our approach requires no initial predictions (e.g., a coarse segmentation mask), shares both encoder and decoder parameters across tasks, and employs a semi-supervised training strategy to learn from scans with missing segmentation labels, a common constraint in real-world clinical data. We evaluated our method on a cohort of 264 patients, where it consistently outperformed state-of-the-art single-task and multi-stage models. For image synthesis, our model achieved a PSNR of 25.61 dB, compared to 23.80 dB from a single-task CDM. For anatomical segmentation, it improved the lumen Dice score to 0.89 from 0.87 and the challenging thrombus Dice score to 0.53 from 0.48 (nnU-Net). These segmentation enhancements led to more accurate clinical measurements, reducing the lumen diameter MAE to 4.19 mm from 5.78 mm and the thrombus area error to 33.85% from 41.45% when compared to nnU-Net. Code is available at https://github.com/yuxuanou623/AortaDiff.git. |
WACV 2026 |
| SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models | 2025-12-04 | ShowReasoning about motion and space is a fundamental cognitive capability that is required by multiple real-world applications. While many studies highlight that large multimodal language models (MLMs) struggle to reason about space, they only focus on static spatial relationships, and not dynamic awareness of motion and space, i.e., reasoning about the effect of egocentric and object motions on spatial relationships. Manually annotating such object and camera movements is expensive. Hence, we introduce SAT, a simulated spatial aptitude training dataset utilizing 3D simulators, comprising both static and dynamic spatial reasoning across 175K question-answer (QA) pairs and 20K scenes. Complementing this, we also construct a small (150 image-QAs) yet challenging dynamic spatial test set using real-world images. Leveraging our SAT datasets and 6 existing static spatial benchmarks, we systematically investigate what improves both static and dynamic spatial awareness. Our results reveal that simulations are surprisingly effective at imparting spatial aptitude to MLMs that translate to real images. We show that perfect annotations in simulation are more effective than existing approaches of pseudo-annotating real images. For instance, SAT training improves a LLaVA-13B model by an average 11% and a LLaVA-Video-7B model by an average 8% on multiple spatial benchmarks, including our real-image dynamic test set and spatial reasoning on long videos -- even outperforming some large proprietary models. While reasoning over static relationships improves with synthetic training data, there is still considerable room for improvement for dynamic reasoning questions. |
Accep...Accepted to COLM 2025. Project webpage: https://arijitray.com/SAT/ |
| SpecTra: Enhancing the Code Translation Ability of Language Models by Generating Multi-Modal Specifications | 2025-12-04 | ShowLarge language models (LLMs) are increasingly being used for the task of automated code translation, which has important real-world applications. However, most existing approaches use only the source code of a program as an input to an LLM, and do not consider the different kinds of specifications that can be extracted from a program. In this paper, we propose SpecTra, a multi-stage approach that uses a novel self-consistency filter to first generate high-quality static specifications, test cases, and natural language descriptions from a given program, and then uses these along with the source code to improve the quality of LLM-generated translations. We evaluate SpecTra on three code translation tasks - C to Rust, C to Go, and JavaScript to TypeScript - and show that it can enhance the performance of six popular LLMs on these tasks by up to a relative improvement of 46%. We also present a case study on extending this approach to handle translation of a full C project to Rust. Our research suggests that generating high-quality specifications could be a promising and efficient way to improve the performance of LLMs for code translation. |
|
| LAET: A Layer-wise Adaptive Ensemble Tuning Framework for Pretrained Language Models | 2025-12-04 | ShowNatural Language Processing (NLP) has transformed the financial industry, enabling advancements in areas such as textual analysis, risk management, and forecasting. Large language models (LLMs) like BloombergGPT and FinMA have set new benchmarks across various financial NLP tasks, including sentiment analysis, stock movement prediction, and credit risk assessment. Furthermore, FinMA-ES, a bilingual financial LLM, has also demonstrated strong performance using the FLARE and FLARE-ES benchmarks. However, the high computational demands of these models limit the accessibility of many organizations. To address this, we propose Layer-wise Adaptive Ensemble Tuning (LAET), a novel strategy that selectively fine-tunes the most effective layers of pre-trained LLMs by analyzing hidden state representations while freezing less critical layers. LAET significantly reduces computational overhead while enhancing task-specific performance. Our approach shows strong results in financial NLP tasks, outperforming existing benchmarks and state-of-the-art LLMs such as GPT-4, even with smaller LLMs ($\sim$3B parameters). This work bridges cutting-edge financial NLP research and real-world deployment with efficient and scalable models for financial applications. |
|
| Light-X: Generative 4D Video Rendering with Camera and Illumination Control | 2025-12-04 | ShowRecent advances in illumination control extend image-based methods to video, yet still facing a trade-off between lighting fidelity and temporal consistency. Moving beyond relighting, a key step toward generative modeling of real-world scenes is the joint control of camera trajectory and illumination, since visual dynamics are inherently shaped by both geometry and lighting. To this end, we present Light-X, a video generation framework that enables controllable rendering from monocular videos with both viewpoint and illumination control. 1) We propose a disentangled design that decouples geometry and lighting signals: geometry and motion are captured via dynamic point clouds projected along user-defined camera trajectories, while illumination cues are provided by a relit frame consistently projected into the same geometry. These explicit, fine-grained cues enable effective disentanglement and guide high-quality illumination. 2) To address the lack of paired multi-view and multi-illumination videos, we introduce Light-Syn, a degradation-based pipeline with inverse-mapping that synthesizes training pairs from in-the-wild monocular footage. This strategy yields a dataset covering static, dynamic, and AI-generated scenes, ensuring robust training. Extensive experiments show that Light-X outperforms baseline methods in joint camera-illumination control and surpasses prior video relighting methods under both text- and background-conditioned settings. |
Proje...Project Page: https://lightx-ai.github.io/ |
| Title | Date | Abstract | Comment |
|---|---|---|---|
| VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM | 2025-12-02 | ShowWe present VIGS-SLAM, a visual-inertial 3D Gaussian Splatting SLAM system that achieves robust real-time tracking and high-fidelity reconstruction. Although recent 3DGS-based SLAM methods achieve dense and photorealistic mapping, their purely visual design degrades under motion blur, low texture, and exposure variations. Our method tightly couples visual and inertial cues within a unified optimization framework, jointly refining camera poses, depths, and IMU states. It features robust IMU initialization, time-varying bias modeling, and loop closure with consistent Gaussian updates. Experiments on four challenging datasets demonstrate our superiority over state-of-the-art methods. Project page: https://vigs-slam.github.io |
Proje...Project page: https://vigs-slam.github.io |
| KM-ViPE: Online Tightly Coupled Vision-Language-Geometry Fusion for Open-Vocabulary Semantic SLAM | 2025-12-01 | ShowWe present KM-ViPE (Knowledge Mapping Video Pose Engine), a real-time open-vocabulary SLAM framework for uncalibrated monocular cameras in dynamic environments. Unlike systems requiring depth sensors and offline calibration, KM-ViPE operates directly on raw RGB streams, making it ideal for ego-centric applications and harvesting internet-scale video data for training. KM-ViPE tightly couples DINO visual features with geometric constraints through a high-level features based adaptive robust kernel that handles both moving objects and movable static objects (e.g., moving furniture in ego-centric views). The system performs simultaneous online localization and open-vocabulary semantic mapping by fusing geometric and deep visual features aligned with language embeddings. Our results are competitive with state-of-the-art approaches, while existing solutions either operate offline, need depth data and/or odometry estimation, or lack dynamic scene robustness. KM-ViPE benefits from internet-scale training and uniquely combines online operation, uncalibrated monocular input, and robust handling of dynamic scenes, which makes it a good fit for autonomous robotics and AR/VR applications and advances practical spatial intelligence capabilities for embodied AI. |
|
| Integration of UWB Radar on Mobile Robots for Continuous Obstacle and Environment Mapping | 2025-11-30 | ShowThis paper presents an infrastructure-free approach for obstacle detection and environmental mapping using ultra-wideband (UWB) radar mounted on a mobile robotic platform. Traditional sensing modalities such as visual cameras and Light Detection and Ranging (LiDAR) fail in environments with poor visibility due to darkness, smoke, or reflective surfaces. In these visioned-impaired conditions, UWB radar offers a promising alternative. To this end, this work explores the suitability of robot-mounted UWB radar for environmental mapping in dynamic, anchor-free scenarios. The study investigates how different materials (metal, concrete and plywood) and UWB radio channels (5 and 9) influence the Channel Impulse Response (CIR). Furthermore, a processing pipeline is proposed to achieve reliable mapping of detected obstacles, consisting of 3 steps: (i) target identification (based on CIR peak detection), (ii) filtering (based on peak properties, signal-to-noise score, and phase-difference of arrival), and (iii) clustering (based on distance estimation and angle-of-arrival estimation). The proposed approach successfully reduces noise and multipath effects, resulting in an obstacle detection precision of at least 82.36% and a recall of 89.46% on channel 9 even when detecting low-reflective materials such as plywood. This work offers a foundation for further development of UWB-based localisation and mapping (SLAM) systems that do not rely on visual features and, unlike conventional UWB localisation systems, do not require on fixed anchor nodes for triangulation. |
This ...This paper has been submitted to IEEE Access Journal and is currently undergoing review |
| DiskChunGS: Large-Scale 3D Gaussian SLAM Through Chunk-Based Memory Management | 2025-11-28 | ShowRecent advances in 3D Gaussian Splatting (3DGS) have demonstrated impressive results for novel view synthesis with real-time rendering capabilities. However, integrating 3DGS with SLAM systems faces a fundamental scalability limitation: methods are constrained by GPU memory capacity, restricting reconstruction to small-scale environments. We present DiskChunGS, a scalable 3DGS SLAM system that overcomes this bottleneck through an out-of-core approach that partitions scenes into spatial chunks and maintains only active regions in GPU memory while storing inactive areas on disk. Our architecture integrates seamlessly with existing SLAM frameworks for pose estimation and loop closure, enabling globally consistent reconstruction at scale. We validate DiskChunGS on indoor scenes (Replica, TUM-RGBD), urban driving scenarios (KITTI), and resource-constrained Nvidia Jetson platforms. Our method uniquely completes all 11 KITTI sequences without memory failures while achieving superior visual quality, demonstrating that algorithmic innovation can overcome the memory constraints that have limited previous 3DGS SLAM methods. |
|
| Estimating Fog Parameters from a Sequence of Stereo Images | 2025-11-25 | ShowWe propose a method which, given a sequence of stereo foggy images, estimates the parameters of a fog model and updates them dynamically. In contrast with previous approaches, which estimate the parameters sequentially and thus are prone to error propagation, our algorithm estimates all the parameters simultaneously by solving a novel optimisation problem. By assuming that fog is only locally homogeneous, our method effectively handles real-world fog, which is often globally inhomogeneous. The proposed algorithm can be easily used as an add-on module in existing visual Simultaneous Localisation and Mapping (SLAM) or odometry systems in the presence of fog. In order to assess our method, we also created a new dataset, the Stereo Driving In Real Fog (SDIRF), consisting of high-quality, consecutive stereo frames of real, foggy road scenes under a variety of visibility conditions, totalling over 40 minutes and 34k frames. As a first-of-its-kind, SDIRF contains the camera's photometric parameters calibrated in a lab environment, which is a prerequisite for correctly applying the atmospheric scattering model to foggy images. The dataset also includes the counterpart clear data of the same routes recorded in overcast weather, which is useful for companion work in image defogging and depth reconstruction. We conducted extensive experiments using both synthetic foggy data and real foggy sequences from SDIRF to demonstrate the superiority of the proposed algorithm over prior methods. Our method not only produces the most accurate estimates on synthetic data, but also adapts better to real fog. We make our code and SDIRF publicly available\footnote{https://github.com/SenseRoboticsLab/estimating-fog-parameters} to the community with the aim of advancing the research on visual perception in fog. |
|
| AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend | 2025-11-25 | ShowWe present AMB3R, a multi-view feed-forward model for dense 3D reconstruction on a metric-scale that addresses diverse 3D vision tasks. The key idea is to leverage a sparse, yet compact, volumetric scene representation as our backend, enabling geometric reasoning with spatial compactness. Although trained solely for multi-view reconstruction, we demonstrate that AMB3R can be seamlessly extended to uncalibrated visual odometry (online) or large-scale structure from motion without the need for task-specific fine-tuning or test-time optimization. Compared to prior pointmap-based models, our approach achieves state-of-the-art performance in camera pose, depth, and metric-scale estimation, 3D reconstruction, and even surpasses optimization-based SLAM and SfM methods with dense reconstruction priors on common benchmarks. |
Proje...Project page: https://hengyiwang.github.io/projects/amber |
| SP-VINS: A Hybrid Stereo Visual Inertial Navigation System based on Implicit Environmental Map | 2025-11-24 | ShowFilter-based visual inertial navigation system (VINS) has attracted mobile-robot researchers for the good balance between accuracy and efficiency, but its limited mapping quality hampers long-term high-accuracy state estimation. To this end, we first propose a novel filter-based stereo VINS, differing from traditional simultaneous localization and mapping (SLAM) systems based on 3D map, which performs efficient loop closure constraints with implicit environmental map composed of keyframes and 2D keypoints. Secondly, we proposed a hybrid residual filter framework that combines landmark reprojection and ray constraints to construct a unified Jacobian matrix for measurement updates. Finally, considering the degraded environment, we incorporated the camera-IMU extrinsic parameters into visual description to achieve online calibration. Benchmark experiments demonstrate that the proposed SP-VINS achieves high computational efficiency while maintaining long-term high-accuracy localization performance, and is superior to existing state-of-the-art (SOTA) methods. |
|
| Stable Multi-Drone GNSS Tracking System for Marine Robots | 2025-11-24 | ShowAccurate localization is essential for marine robotics, yet Global Navigation Satellite System (GNSS) signals are unreliable or unavailable even at a very short distance below the water surface. Traditional alternatives, such as inertial navigation, Doppler Velocity Loggers (DVL), SLAM, and acoustic methods, suffer from error accumulation, high computational demands, or infrastructure dependence. In this work, we present a scalable multi-drone GNSS-based tracking system for surface and near-surface marine robots. Our approach combines efficient visual detection, lightweight multi-object tracking, GNSS-based triangulation, and a confidence-weighted Extended Kalman Filter (EKF) to provide stable GNSS estimation in real time. We further introduce a cross-drone tracking ID alignment algorithm that enforces global consistency across views, enabling robust multi-robot tracking with redundant aerial coverage. We validate our system in diversified complex settings to show the scalability and robustness of the proposed algorithm. |
|
| Unreal Robotics Lab: A High-Fidelity Robotics Simulator with Advanced Physics and Rendering | 2025-11-23 | ShowHigh-fidelity simulation is essential for robotics research, enabling safe and efficient testing of perception, control, and navigation algorithms. However, achieving both photorealistic rendering and accurate physics modeling remains a challenge. This paper presents a novel simulation framework, the Unreal Robotics Lab (URL), that integrates the advanced rendering capabilities of the Unreal Engine with MuJoCo's high-precision physics simulation. Our approach enables realistic robotic perception while maintaining accurate physical interactions, facilitating benchmarking and dataset generation for vision-based robotics applications. The system supports complex environmental effects, such as smoke, fire, and water dynamics, which are critical to evaluating robotic performance under adverse conditions. We benchmark visual navigation and SLAM methods within our framework, demonstrating its utility for testing real-world robustness in controlled yet diverse scenarios. By bridging the gap between physics accuracy and photorealistic rendering, our framework provides a powerful tool for advancing robotics research and sim-to-real transfer. Our open-source framework is available at https://unrealroboticslab.github.io/. |
|
| Gaze Beyond the Frame: Forecasting Egocentric 3D Visual Span | 2025-11-23 | ShowPeople continuously perceive and interact with their surroundings based on underlying intentions that drive their exploration and behaviors. While research in egocentric user and scene understanding has focused primarily on motion and contact-based interaction, forecasting human visual perception itself remains less explored despite its fundamental role in guiding human actions and its implications for AR/VR and assistive technologies. We address the challenge of egocentric 3D visual span forecasting, predicting where a person's visual perception will focus next within their three-dimensional environment. To this end, we propose EgoSpanLift, a novel method that transforms egocentric visual span forecasting from 2D image planes to 3D scenes. EgoSpanLift converts SLAM-derived keypoints into gaze-compatible geometry and extracts volumetric visual span regions. We further combine EgoSpanLift with 3D U-Net and unidirectional transformers, enabling spatio-temporal fusion to efficiently predict future visual span in the 3D grid. In addition, we curate a comprehensive benchmark from raw egocentric multisensory data, creating a testbed with 364.6K samples for 3D visual span forecasting. Our approach outperforms competitive baselines for egocentric 2D gaze anticipation and 3D localization while achieving comparable results even when projected back onto 2D image planes without additional 2D-specific training. |
NeurI...NeurIPS 2025 Spotlight |
| Unobservable Subspace Evolution and Alignment for Consistent Visual-Inertial Navigation | 2025-11-22 | ShowThe inconsistency issue in the Visual-Inertial Navigation System (VINS) is a long-standing and fundamental challenge. While existing studies primarily attribute the inconsistency to observability mismatch, these analyses are often based on simplified theoretical formulations that consider only prediction and SLAM correction. Such formulations fail to cover the non-standard estimation steps, such as MSCKF correction and delayed initialization, which are critical for practical VINS estimators. Furthermore, the lack of a comprehensive understanding of how inconsistency dynamically emerges across estimation steps has hindered the development of precise and efficient solutions. As a result, current approaches often face a trade-off between estimator accuracy, consistency, and implementation complexity. To address these limitations, this paper proposes a novel analysis framework termed Unobservable Subspace Evolution (USE), which systematically characterizes how the unobservable subspace evolves throughout the entire estimation pipeline by explicitly tracking changes in its evaluation points. This perspective sheds new light on how individual estimation steps contribute to inconsistency. Our analysis reveals that observability misalignment induced by certain steps is the antecedent of observability mismatch. Guided by this insight, we propose a simple yet effective solution paradigm, Unobservable Subspace Alignment (USA), which eliminates inconsistency by selectively intervening only in those estimation steps that induce misalignment. We design two USA methods: transformation-based and re-evaluation-based, both offering accurate and computationally lightweight solutions. Extensive simulations and real-world experiments validate the effectiveness of the proposed methods. |
20 pages, 16 figures |
| DynoSAM: Open-Source Smoothing and Mapping Framework for Dynamic SLAM | 2025-11-20 | ShowTraditional Visual Simultaneous Localization and Mapping (vSLAM) systems focus solely on static scene structures, overlooking dynamic elements in the environment. Although effective for accurate visual odometry in complex scenarios, these methods discard crucial information about moving objects. By incorporating this information into a Dynamic SLAM framework, the motion of dynamic entities can be estimated, enhancing navigation whilst ensuring accurate localization. However, the fundamental formulation of Dynamic SLAM remains an open challenge, with no consensus on the optimal approach for accurate motion estimation within a SLAM pipeline. Therefore, we developed DynoSAM, an open-source framework for Dynamic SLAM that enables the efficient implementation, testing, and comparison of various Dynamic SLAM optimization formulations. DynoSAM integrates static and dynamic measurements into a unified optimization problem solved using factor graphs, simultaneously estimating camera poses, static scene, object motion or poses, and object structures. We evaluate DynoSAM across diverse simulated and real-world datasets, achieving state-of-the-art motion estimation in indoor and outdoor environments, with substantial improvements over existing systems. Additionally, we demonstrate DynoSAM utility in downstream applications, including 3D reconstruction of dynamic scenes and trajectory prediction, thereby showcasing potential for advancing dynamic object-aware SLAM systems. DynoSAM is open-sourced at https://github.com/ACFR-RPG/DynOSAM. |
20 pa...20 pages, 10 figures. Submitted to T-RO Visual SLAM SI 2025 |
| CRISTAL: Real-time Camera Registration in Static LiDAR Scans using Neural Rendering | 2025-11-20 | ShowAccurate camera localization is crucial for robotics and Extended Reality (XR), enabling reliable navigation and alignment of virtual and real content. Existing visual methods often suffer from drift, scale ambiguity, and depend on fiducials or loop closure. This work introduces a real-time method for localizing a camera within a pre-captured, highly accurate colored LiDAR point cloud. By rendering synthetic views from this cloud, 2D-3D correspondences are established between live frames and the point cloud. A neural rendering technique narrows the domain gap between synthetic and real images, reducing occlusion and background artifacts to improve feature matching. The result is drift-free camera tracking with correct metric scale in the global LiDAR coordinate system. Two real-time variants are presented: Online Render and Match, and Prebuild and Localize. We demonstrate improved results on the ScanNet++ dataset and outperform existing SLAM pipelines. |
|
| PuzzlePoles: Cylindrical Fiducial Markers Based on the PuzzleBoard Pattern | 2025-11-18 | ShowReliable perception of the environment is a key enabler for autonomous systems, where calibration and localization tasks often rely on robust visual markers. We introduce the PuzzlePole, a new type of fiducial markers derived from the recently proposed PuzzleBoard calibration pattern. The PuzzlePole is a cylindrical marker, enabling reliable recognition and pose estimation from 360° viewing direction. By leveraging the unique combinatorial structure of the PuzzleBoard pattern, PuzzlePoles provide a high accuracy in localization and orientation while being robust to occlusions. The design offers flexibility for deployment in diverse autonomous systems scenarios, ranging from robot navigation and SLAM to tangible interfaces. |
|
| iGaussian: Real-Time Camera Pose Estimation via Feed-Forward 3D Gaussian Splatting Inversion | 2025-11-18 | ShowRecent trends in SLAM and visual navigation have embraced 3D Gaussians as the preferred scene representation, highlighting the importance of estimating camera poses from a single image using a pre-built Gaussian model. However, existing approaches typically rely on an iterative \textit{render-compare-refine} loop, where candidate views are first rendered using NeRF or Gaussian Splatting, then compared against the target image, and finally, discrepancies are used to update the pose. This multi-round process incurs significant computational overhead, hindering real-time performance in robotics. In this paper, we propose iGaussian, a two-stage feed-forward framework that achieves real-time camera pose estimation through direct 3D Gaussian inversion. Our method first regresses a coarse 6DoF pose using a Gaussian Scene Prior-based Pose Regression Network with spatial uniform sampling and guided attention mechanisms, then refines it through feature matching and multi-model fusion. The key contribution lies in our cross-correlation module that aligns image embeddings with 3D Gaussian attributes without differentiable rendering, coupled with a Weighted Multiview Predictor that fuses features from Multiple strategically sampled viewpoints. Experimental results on the NeRF Synthetic, Mip-NeRF 360, and T&T+DB datasets demonstrate a significant performance improvement over previous methods, reducing median rotation errors to 0.2° while achieving 2.87 FPS tracking on mobile robots, which is an impressive 10 times speedup compared to optimization-based approaches. Code: https://github.com/pythongod-exe/iGaussian |
IROS 2025 |
| DPVO-QAT++: Heterogeneous QAT and CUDA Kernel Fusion for High-Performance Deep Patch Visual Odometry | 2025-11-16 | ShowDeep learning-based Visual SLAM (vSLAM) systems exhibit exceptional geometric reasoning capabilities, yet their prohibitive computational overhead severely restricts deployment on resource-constrained autonomous platforms. This paper presents a hierarchical quantization optimization framework, DPVO-QAT++ (DPVO-QAT++: Heterogeneous QAT and CUDA Kernel Fusion for High-Performance Deep Patch Visual Odometry). Through the synergistic integration of learnable scale parameterization, a heterogeneous precision design for the Visual Odometry (VO) front-end and back-end (front-end floating-point fake quantization with FP16/FP32; back-end full precision), and GPU-native kernel fusion for fake quantization (custom CUDA kernels), our framework significantly reduces memory footprint and increases processing speed while preserving the trajectory accuracy of the original model. On the TartanAir dataset, our framework achieves an average FPS increase of 52.1%, a 29.1% reduction in median latency, and a 64.9% reduction in peak GPU memory reservation, while maintaining trajectory accuracy (ATE) comparable to the original DPVO model across 32 validation sequences. On the EuRoC dataset, it realizes an average FPS increase of 30.1%, a 23.1% reduction in median latency, and a 37.7% reduction in peak GPU memory reservation, maintaining comparable trajectory accuracy (ATE) across 11 validation sequences. Experimental results demonstrate that DPVO-QAT++ effectively bridges the gap between high-precision deep VO and the efficiency requirements for practical deployment, offering a viable engineering paradigm for the application of this technology on real-world embedded platforms. Keywords: Visual Odometry, Heterogeneous Precision Architecture, Quantization-Aware Training, CUDA Kernel Fusion, Scale-Only Training, Deep Patch Visual Odometry, GPU-Native Kernel Fusion. |
|
| MASt3R-Fusion: Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAM | 2025-11-16 | ShowVisual SLAM is a cornerstone technique in robotics, autonomous driving and extended reality (XR), yet classical systems often struggle with low-texture environments, scale ambiguity, and degraded performance under challenging visual conditions. Recent advancements in feed-forward neural network-based pointmap regression have demonstrated the potential to recover high-fidelity 3D scene geometry directly from images, leveraging learned spatial priors to overcome limitations of traditional multi-view geometry methods. However, the widely validated advantages of probabilistic multi-sensor information fusion are often discarded in these pipelines. In this work, we propose MASt3R-Fusion,a multi-sensor-assisted visual SLAM framework that tightly integrates feed-forward pointmap regression with complementary sensor information, including inertial measurements and GNSS data. The system introduces Sim(3)-based visualalignment constraints (in the Hessian form) into a universal metric-scale SE(3) factor graph for effective information fusion. A hierarchical factor graph design is developed, which allows both real-time sliding-window optimization and global optimization with aggressive loop closures, enabling real-time pose tracking, metric-scale structure perception and globally consistent mapping. We evaluate our approach on both public benchmarks and self-collected datasets, demonstrating substantial improvements in accuracy and robustness over existing visual-centered multi-sensor SLAM systems. The code will be released open-source to support reproducibility and further research (https://github.com/GREAT-WHU/MASt3R-Fusion). |
|
| ICD-Net: Inertial Covariance Displacement Network for Drone Visual-Inertial SLAM | 2025-11-13 | ShowVisual-inertial SLAM systems often exhibit suboptimal performance due to multiple confounding factors including imperfect sensor calibration, noisy measurements, rapid motion dynamics, low illumination, and the inherent limitations of traditional inertial navigation integration methods. These issues are particularly problematic in drone applications where robust and accurate state estimation is critical for safe autonomous operation. In this work, we present ICD-Net, a novel framework that enhances visual-inertial SLAM performance by learning to process raw inertial measurements and generating displacement estimates with associated uncertainty quantification. Rather than relying on analytical inertial sensor models that struggle with real-world sensor imperfections, our method directly extracts displacement maps from sensor data while simultaneously predicting measurement covariances that reflect estimation confidence. We integrate ICD-Net outputs as additional residual constraints into the VINS-Fusion optimization framework, where the predicted uncertainties appropriately weight the neural network contributions relative to traditional visual and inertial terms. The learned displacement constraints provide complementary information that compensates for various error sources in the SLAM pipeline. Our approach can be used under both normal operating conditions and in situations of camera inconsistency or visual degradation. Experimental evaluation on challenging high-speed drone sequences demonstrated that our approach significantly improved trajectory estimation accuracy compared to standard VINS-Fusion, with more than 38% improvement in mean APE and uncertainty estimates proving crucial for maintaining system robustness. Our method shows that neural network enhancement can effectively address multiple sources of SLAM degradation while maintaining real-time performance requirements. |
|
| vS-Graphs: Tightly Coupling Visual SLAM and 3D Scene Graphs Exploiting Hierarchical Scene Understanding | 2025-11-12 | ShowCurrent Visual Simultaneous Localization and Mapping (VSLAM) systems often struggle to create maps that are both semantically rich and easily interpretable. While incorporating semantic scene knowledge aids in building richer maps with contextual associations among mapped objects, representing them in structured formats, such as scene graphs, has not been widely addressed, resulting in complex map comprehension and limited scalability. This paper introduces vS-Graphs, a novel real-time VSLAM framework that integrates vision-based scene understanding with map reconstruction and comprehensible graph-based representation. The framework infers structural elements (i.e., rooms and floors) from detected building components (i.e., walls and ground surfaces) and incorporates them into optimizable 3D scene graphs. This solution enhances the reconstructed map's semantic richness, comprehensibility, and localization accuracy. Extensive experiments on standard benchmarks and real-world datasets demonstrate that vS-Graphs achieves an average of 15.22% accuracy gain across all tested datasets compared to state-of-the-art VSLAM methods. Furthermore, the proposed framework achieves environment-driven semantic entity detection accuracy comparable to that of precise LiDAR-based frameworks, using only visual features. The code is publicly available at https://github.com/snt-arg/visual_sgraphs and is actively being improved. Moreover, a web page containing more media and evaluation outcomes is available on https://snt-arg.github.io/vsgraphs-results/. |
19 pa...19 pages, 10 figures, 5 tables |
| DualVision ArthroNav: Investigating Opportunities to Enhance Localization and Reconstruction in Image-based Arthroscopy Navigation via External Cameras | 2025-11-12 | ShowArthroscopic procedures can greatly benefit from navigation systems that enhance spatial awareness, depth perception, and field of view. However, existing optical tracking solutions impose strict workspace constraints and disrupt surgical workflow. Vision-based alternatives, though less invasive, often rely solely on the monocular arthroscope camera, making them prone to drift, scale ambiguity, and sensitivity to rapid motion or occlusion. We propose DualVision ArthroNav, a multi-camera arthroscopy navigation system that integrates an external camera rigidly mounted on the arthroscope. The external camera provides stable visual odometry and absolute localization, while the monocular arthroscope video enables dense scene reconstruction. By combining these complementary views, our system resolves the scale ambiguity and long-term drift inherent in monocular SLAM and ensures robust relocalization. Experiments demonstrate that our system effectively compensates for calibration errors, achieving an average absolute trajectory error of 1.09 mm. The reconstructed scenes reach an average target registration error of 2.16 mm, with high visual fidelity (SSIM = 0.69, PSNR = 22.19). These results indicate that our system provides a practical and cost-efficient solution for arthroscopic navigation, bridging the gap between optical tracking and purely vision-based systems, and paving the way toward clinically deployable, fully vision-based arthroscopic guidance. |
|
| UMIGen: A Unified Framework for Egocentric Point Cloud Generation and Cross-Embodiment Robotic Imitation Learning | 2025-11-12 | ShowData-driven robotic learning faces an obvious dilemma: robust policies demand large-scale, high-quality demonstration data, yet collecting such data remains a major challenge owing to high operational costs, dependence on specialized hardware, and the limited spatial generalization capability of current methods. The Universal Manipulation Interface (UMI) relaxes the strict hardware requirements for data collection, but it is restricted to capturing only RGB images of a scene and omits the 3D geometric information on which many tasks rely. Inspired by DemoGen, we propose UMIGen, a unified framework that consists of two key components: (1) Cloud-UMI, a handheld data collection device that requires no visual SLAM and simultaneously records point cloud observation-action pairs; and (2) a visibility-aware optimization mechanism that extends the DemoGen pipeline to egocentric 3D observations by generating only points within the camera's field of view. These two components enable efficient data generation that aligns with real egocentric observations and can be directly transferred across different robot embodiments without any post-processing. Experiments in both simulated and real-world settings demonstrate that UMIGen supports strong cross-embodiment generalization and accelerates data collection in diverse manipulation tasks. |
|
| Integration of Visual SLAM into Consumer-Grade Automotive Localization | 2025-11-10 | ShowAccurate ego-motion estimation in consumer-grade vehicles currently relies on proprioceptive sensors, i.e. wheel odometry and IMUs, whose performance is limited by systematic errors and calibration. While visual-inertial SLAM has become a standard in robotics, its integration into automotive ego-motion estimation remains largely unexplored. This paper investigates how visual SLAM can be integrated into consumer-grade vehicle localization systems to improve performance. We propose a framework that fuses visual SLAM with a lateral vehicle dynamics model to achieve online gyroscope calibration under realistic driving conditions. Experimental results demonstrate that vision-based integration significantly improves gyroscope calibration accuracy and thus enhances overall localization performance, highlighting a promising path toward higher automotive localization accuracy. We provide results on both proprietary and public datasets, showing improved performance and superior localization accuracy on a public benchmark compared to state-of-the-art methods. |
This ...This manuscript has been submitted to the IEEE for possible publication |
| Multi-cam Multi-map Visual Inertial Localization: System, Validation and Dataset | 2025-11-08 | ShowRobot control loops require causal pose estimates that depend only on past and present measurements. At each timestep, controllers compute commands using the current pose without waiting for future refinements. While traditional visual SLAM systems achieve high accuracy through retrospective loop closures, these corrections arrive after control decisions were already executed, violating causality. Visual-inertial odometry maintains causality but accumulates unbounded drift over time. To address the distinct requirements of robot control, we propose a multi-camera multi-map visual-inertial localization system providing real-time, causal pose estimation with bounded localization error through continuous map constraints. Since standard trajectory metrics evaluate post-processed trajectories, we analyze the error composition of map-based localization systems and propose a set of evaluation metrics suitable for measuring causal localization performance. To validate our system, we design a multi-camera IMU hardware setup and collect a challenging long-term campus dataset featuring diverse illumination and seasonal conditions. Experimental results on public benchmarks and on our own collected dataset demonstrate that our system provides significantly higher real-time localization accuracy compared to other methods. To benefit the community, we have made both the system and the dataset open source at https://anonymous.4open.science/r/Multi-cam-Multi-map-VILO-7993. |
|
| 3D Mapping Using a Lightweight and Low-Power Monocular Camera Embedded inside a Gripper of Limbed Climbing Robots | 2025-11-08 | ShowLimbed climbing robots are designed to explore challenging vertical walls, such as the skylights of the Moon and Mars. In such robots, the primary role of a hand-eye camera is to accurately estimate 3D positions of graspable points (i.e., convex terrain surfaces) thanks to its close-up views. While conventional climbing robots often employ RGB-D cameras as hand-eye cameras to facilitate straightforward 3D terrain mapping and graspable point detection, RGB-D cameras are large and consume considerable power. This work presents a 3D terrain mapping system designed for space exploration using limbed climbing robots equipped with a monocular hand-eye camera. Compared to RGB-D cameras, monocular cameras are more lightweight, compact structures, and have lower power consumption. Although monocular SLAM can be used to construct 3D maps, it suffers from scale ambiguity. To address this limitation, we propose a SLAM method that fuses monocular visual constraints with limb forward kinematics. The proposed method jointly estimates time-series gripper poses and the global metric scale of the 3D map based on factor graph optimization. We validate the proposed framework through both physics-based simulations and real-world experiments. The results demonstrate that our framework constructs a metrically scaled 3D terrain map in real-time and enables autonomous grasping of convex terrain surfaces using a monocular hand-eye camera, without relying on RGB-D cameras. Our method contributes to scalable and energy-efficient perception for future space missions involving limbed climbing robots. See the video summary here: https://youtu.be/fMBrrVNKJfc |
Inter...International Conference on Space Robotics (iSpaRo) |
| Multi-modal Loop Closure Detection with Foundation Models in Severely Unstructured Environments | 2025-11-07 | ShowRobust loop closure detection is a critical component of Simultaneous Localization and Mapping (SLAM) algorithms in GNSS-denied environments, such as in the context of planetary exploration. In these settings, visual place recognition often fails due to aliasing and weak textures, while LiDAR-based methods suffer from sparsity and ambiguity. This paper presents MPRF, a multimodal pipeline that leverages transformer-based foundation models for both vision and LiDAR modalities to achieve robust loop closure in severely unstructured environments. Unlike prior work limited to retrieval, MPRF integrates a two-stage visual retrieval strategy with explicit 6-DoF pose estimation, combining DINOv2 features with SALAD aggregation for efficient candidate screening and SONATA-based LiDAR descriptors for geometric verification. Experiments on the S3LI dataset and S3LI Vulcano dataset show that MPRF outperforms state-of-the-art retrieval methods in precision while enhancing pose estimation robustness in low-texture regions. By providing interpretable correspondences suitable for SLAM back-ends, MPRF achieves a favorable trade-off between accuracy, efficiency, and reliability, demonstrating the potential of foundation models to unify place recognition and pose estimation. Code and models will be released at github.com/DLR-RM/MPRF. |
Under...Under review for ICRA 2026 |
| MLP-SLAM: Multilayer Perceptron-Based Simultaneous Localization and Mapping | 2025-11-06 | ShowThe Visual Simultaneous Localization and Mapping (V-SLAM) system has seen significant development in recent years, demonstrating high precision in environments with limited dynamic objects. However, their performance significantly deteriorates when deployed in settings with a higher presence of movable objects, such as environments with pedestrians, cars, and buses, which are common in outdoor scenes. To address this issue, we propose a Multilayer Perceptron (MLP)-based real-time stereo SLAM system that leverages complete geometry information to avoid information loss. Moreover, there is currently no publicly available dataset for directly evaluating the effectiveness of dynamic and static feature classification methods, and to bridge this gap, we have created a publicly available dataset containing over 50,000 feature points. Experimental results demonstrate that our MLP-based dynamic and static feature point discriminator has achieved superior performance compared to other methods on this dataset. Furthermore, the MLP-based real-time stereo SLAM system has shown the highest average precision and fastest speed on the outdoor KITTI tracking datasets compared to other dynamic SLAM systems.The open-source code and datasets are available at https://github.com/TaozheLi/MLP-SLAM. |
Dynamic SLAM |
| TurboMap: GPU-Accelerated Local Mapping for Visual SLAM | 2025-11-03 | ShowThis paper presents TurboMap, a GPU-accelerated and CPU-optimized local mapping module for visual SLAM systems. We identify key performance bottlenecks in the local mapping process for visual SLAM and address them through targeted GPU and CPU optimizations. Specifically, we offload map point triangulation and fusion to the GPU, accelerate redundant keyframe culling on the CPU, and integrate a GPU-accelerated solver to speed up local bundle adjustment. Our implementation is built on top of ORB-SLAM3 and leverages CUDA for GPU programming. The experimental results show that TurboMap achieves an average speedup of 1.3x in the EuRoC dataset and 1.6x in the TUM-VI dataset in the local mapping module, on both desktop and embedded platforms, while maintaining the accuracy of the original system. |
Submi...Submitted to ICRA 2026 |
| AgriGS-SLAM: Orchard Mapping Across Seasons via Multi-View Gaussian Splatting SLAM | 2025-10-30 | ShowAutonomous robots in orchards require real-time 3D scene understanding despite repetitive row geometry, seasonal appearance changes, and wind-driven foliage motion. We present AgriGS-SLAM, a Visual--LiDAR SLAM framework that couples direct LiDAR odometry and loop closures with multi-camera 3D Gaussian Splatting (3DGS) rendering. Batch rasterization across complementary viewpoints recovers orchard structure under occlusions, while a unified gradient-driven map lifecycle executed between keyframes preserves fine details and bounds memory. Pose refinement is guided by a probabilistic LiDAR-based depth consistency term, back-propagated through the camera projection to tighten geometry-appearance coupling. We deploy the system on a field platform in apple and pear orchards across dormancy, flowering, and harvesting, using a standardized trajectory protocol that evaluates both training-view and novel-view synthesis to reduce 3DGS overfitting in evaluation. Across seasons and sites, AgriGS-SLAM delivers sharper, more stable reconstructions and steadier trajectories than recent state-of-the-art 3DGS-SLAM baselines while maintaining real-time performance on-tractor. While demonstrated in orchard monitoring, the approach can be applied to other outdoor domains requiring robust multimodal perception. |
|
| Loop Closure from Two Views: Revisiting PGO for Scalable Trajectory Estimation through Monocular Priors | 2025-10-30 | Show(Visual) Simultaneous Localization and Mapping (SLAM) remains a fundamental challenge in enabling autonomous systems to navigate and understand large-scale environments. Traditional SLAM approaches struggle to balance efficiency and accuracy, particularly in large-scale settings where extensive computational resources are required for scene reconstruction and Bundle Adjustment (BA). However, this scene reconstruction, in the form of sparse pointclouds of visual landmarks, is often only used within the SLAM system because navigation and planning methods require different map representations. In this work, we therefore investigate a more scalable Visual SLAM (VSLAM) approach without reconstruction, mainly based on approaches for two-view loop closures. By restricting the map to a sparse keyframed pose graph without dense geometry representations, our `2GO' system achieves efficient optimization with competitive absolute trajectory accuracy. In particular, we find that recent advancements in image matching and monocular depth priors enable very accurate trajectory optimization without BA. We conduct extensive experiments on diverse datasets, including large-scale scenarios, and provide a detailed analysis of the trade-offs between runtime, accuracy, and map size. Our results demonstrate that this streamlined approach supports real-time performance, scales well in map size and trajectory duration, and effectively broadens the capabilities of VSLAM for long-duration deployments to large environments. |
|
| Exploring Object-Aware Attention Guided Frame Association for RGB-D SLAM | 2025-10-30 | ShowAttention models have recently emerged as a powerful approach, demonstrating significant progress in various fields. Visualization techniques, such as class activation mapping, provide visual insights into the reasoning of convolutional neural networks (CNNs). Using network gradients, it is possible to identify regions where the network pays attention during image recognition tasks. Furthermore, these gradients can be combined with CNN features to localize more generalizable, task-specific attentive (salient) regions within scenes. However, explicit use of this gradient-based attention information integrated directly into CNN representations for semantic object understanding remains limited. Such integration is particularly beneficial for visual tasks like simultaneous localization and mapping (SLAM), where CNN representations enriched with spatially attentive object locations can enhance performance. In this work, we propose utilizing task-specific network attention for RGB-D indoor SLAM. Specifically, we integrate layer-wise attention information derived from network gradients with CNN feature representations to improve frame association performance. Experimental results indicate improved performance compared to baseline methods, particularly for large environments. |
doubl...double-column 5 pages, 3 figures |
| GeVI-SLAM: Gravity-Enhanced Stereo Visua Inertial SLAM for Underwater Robots | 2025-10-28 | ShowAccurate visual inertial simultaneous localization and mapping (VI SLAM) for underwater robots remains a significant challenge due to frequent visual degeneracy and insufficient inertial measurement unit (IMU) motion excitation. In this paper, we present GeVI-SLAM, a gravity-enhanced stereo VI SLAM system designed to address these issues. By leveraging the stereo camera's direct depth estimation ability, we eliminate the need to estimate scale during IMU initialization, enabling stable operation even under low acceleration dynamics. With precise gravity initialization, we decouple the pitch and roll from the pose estimation and solve a 4 degrees of freedom (DOF) Perspective-n-Point (PnP) problem for pose tracking. This allows the use of a minimal 3-point solver, which significantly reduces computational time to reject outliers within a Random Sample Consensus framework. We further propose a bias-eliminated 4-DOF PnP estimator with provable consistency, ensuring the relative pose converges to the true value as the feature number increases. To handle dynamic motion, we refine the full 6-DOF pose while jointly estimating the IMU covariance, enabling adaptive weighting of the gravity prior. Extensive experiments on simulated and real-world data demonstrate that GeVI-SLAM achieves higher accuracy and greater stability compared to state-of-the-art methods. |
|
| LVD-GS: Gaussian Splatting SLAM for Dynamic Scenes via Hierarchical Explicit-Implicit Representation Collaboration Rendering | 2025-10-26 | Show3D Gaussian Splatting SLAM has emerged as a widely used technique for high-fidelity mapping in spatial intelligence. However, existing methods often rely on a single representation scheme, which limits their performance in large-scale dynamic outdoor scenes and leads to cumulative pose errors and scale ambiguity. To address these challenges, we propose \textbf{LVD-GS}, a novel LiDAR-Visual 3D Gaussian Splatting SLAM system. Motivated by the human chain-of-thought process for information seeking, we introduce a hierarchical collaborative representation module that facilitates mutual reinforcement for mapping optimization, effectively mitigating scale drift and enhancing reconstruction robustness. Furthermore, to effectively eliminate the influence of dynamic objects, we propose a joint dynamic modeling module that generates fine-grained dynamic masks by fusing open-world segmentation with implicit residual constraints, guided by uncertainty estimates from DINO-Depth features. Extensive evaluations on KITTI, nuScenes, and self-collected datasets demonstrate that our approach achieves state-of-the-art performance compared to existing methods. |
|
| RoGER-SLAM: A Robust Gaussian Splatting SLAM System for Noisy and Low-light Environment Resilience | 2025-10-26 | ShowThe reliability of Simultaneous Localization and Mapping (SLAM) is severely constrained in environments where visual inputs suffer from noise and low illumination. Although recent 3D Gaussian Splatting (3DGS) based SLAM frameworks achieve high-fidelity mapping under clean conditions, they remain vulnerable to compounded degradations that degrade mapping and tracking performance. A key observation underlying our work is that the original 3DGS rendering pipeline inherently behaves as an implicit low-pass filter, attenuating high-frequency noise but also risking over-smoothing. Building on this insight, we propose RoGER-SLAM, a robust 3DGS SLAM system tailored for noise and low-light resilience. The framework integrates three innovations: a Structure-Preserving Robust Fusion (SP-RoFusion) mechanism that couples rendered appearance, depth, and edge cues; an adaptive tracking objective with residual balancing regularization; and a Contrastive Language-Image Pretraining (CLIP)-based enhancement module, selectively activated under compounded degradations to restore semantic and structural fidelity. Comprehensive experiments on Replica, TUM, and real-world sequences show that RoGER-SLAM consistently improves trajectory accuracy and reconstruction quality compared with other 3DGS-SLAM systems, especially under adverse imaging conditions. |
13 pa...13 pages, 11 figures, under review |
| Bag-of-Word-Groups (BoWG): A Robust and Efficient Loop Closure Detection Method Under Perceptual Aliasing | 2025-10-26 | ShowLoop closure is critical in Simultaneous Localization and Mapping (SLAM) systems to reduce accumulative drift and ensure global mapping consistency. However, conventional methods struggle in perceptually aliased environments, such as narrow pipes, due to vector quantization, feature sparsity, and repetitive textures, while existing solutions often incur high computational costs. This paper presents Bag-of-Word-Groups (BoWG), a novel loop closure detection method that achieves superior precision-recall, robustness, and computational efficiency. The core innovation lies in the introduction of word groups, which captures the spatial co-occurrence and proximity of visual words to construct an online dictionary. Additionally, drawing inspiration from probabilistic transition models, we incorporate temporal consistency directly into similarity computation with an adaptive scheme, substantially improving precision-recall performance. The method is further strengthened by a feature distribution analysis module and dedicated post-verification mechanisms. To evaluate the effectiveness of our method, we conduct experiments on both public datasets and a confined-pipe dataset we constructed. Results demonstrate that BoWG surpasses state-of-the-art methods, including both traditional and learning-based approaches, in terms of precision-recall and computational efficiency. Our approach also exhibits excellent scalability, achieving an average processing time of 16 ms per image across 17,565 images in the Bicocca25b dataset. |
This ...This paper has been accepted by IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2025 |
| Underwater Visual-Inertial-Acoustic-Depth SLAM with DVL Preintegration for Degraded Environments | 2025-10-24 | ShowVisual degradation caused by limited visibility, insufficient lighting, and feature scarcity in underwater environments presents significant challenges to visual-inertial simultaneous localization and mapping (SLAM) systems. To address these challenges, this paper proposes a graph-based visual-inertial-acoustic-depth SLAM system that integrates a stereo camera, an inertial measurement unit (IMU), the Doppler velocity log (DVL), and a pressure sensor. The key innovation lies in the tight integration of four distinct sensor modalities to ensure reliable operation, even under degraded visual conditions. To mitigate DVL drift and improve measurement efficiency, we propose a novel velocity-bias-based DVL preintegration strategy. At the frontend, hybrid tracking strategies and acoustic-inertial-depth joint optimization enhance system stability. Additionally, multi-source hybrid residuals are incorporated into a graph optimization framework. Extensive quantitative and qualitative analyses of the proposed system are conducted in both simulated and real-world underwater scenarios. The results demonstrate that our approach outperforms current state-of-the-art stereo visual-inertial SLAM systems in both stability and localization accuracy, exhibiting exceptional robustness, particularly in visually challenging environments. |
10 pages, 10 figures |
| Deep Learning-Powered Visual SLAM Aimed at Assisting Visually Impaired Navigation | 2025-10-23 | ShowDespite advancements in SLAM technologies, robust operation under challenging conditions such as low-texture, motion-blur, or challenging lighting remains an open challenge. Such conditions are common in applications such as assistive navigation for the visually impaired. These challenges undermine localization accuracy and tracking stability, reducing navigation reliability and safety. To overcome these limitations, we present SELM-SLAM3, a deep learning-enhanced visual SLAM framework that integrates SuperPoint and LightGlue for robust feature extraction and matching. We evaluated our framework using TUM RGB-D, ICL-NUIM, and TartanAir datasets, which feature diverse and challenging scenarios. SELM-SLAM3 outperforms conventional ORB-SLAM3 by an average of 87.84% and exceeds state-of-the-art RGB-D SLAM systems by 36.77%. Our framework demonstrates enhanced performance under challenging conditions, such as low-texture scenes and fast motion, providing a reliable platform for developing navigation aids for the visually impaired. |
8 pag...8 pages, 7 figures, 4 tables |
| DeepDetect: Learning All-in-One Dense Keypoints | 2025-10-21 | ShowKeypoint detection is the foundation of many computer vision tasks, including image registration, structure-from motion, 3D reconstruction, visual odometry, and SLAM. Traditional detectors (SIFT, SURF, ORB, BRISK, etc.) and learning based methods (SuperPoint, R2D2, LF-Net, D2-Net, etc.) have shown strong performance yet suffer from key limitations: sensitivity to photometric changes, low keypoint density and repeatability, limited adaptability to challenging scenes, and lack of semantic understanding, often failing to prioritize visually important regions. We present DeepDetect, an intelligent, all-in-one, dense keypoint detector that unifies the strengths of classical detectors using deep learning. Firstly, we create ground-truth masks by fusing outputs of 7 keypoint and 2 edge detectors, extracting diverse visual cues from corners and blobs to prominent edges and textures in the images. Afterwards, a lightweight and efficient model: ESPNet, is trained using these masks as labels, enabling DeepDetect to focus semantically on images while producing highly dense keypoints, that are adaptable to diverse and visually degraded conditions. Evaluations on the Oxford Affine Covariant Regions dataset demonstrate that DeepDetect surpasses other detectors in keypoint density, repeatability, and the number of correct matches, achieving maximum values of 0.5143 (average keypoint density), 0.9582 (average repeatability), and 59,003 (correct matches). |
6 pag...6 pages, 6 figures, 2 tables, 7 equations |
| VAR-SLAM: Visual Adaptive and Robust SLAM for Dynamic Environments | 2025-10-17 | ShowVisual SLAM in dynamic environments remains challenging, as several existing methods rely on semantic filtering that only handles known object classes, or use fixed robust kernels that cannot adapt to unknown moving objects, leading to degraded accuracy when they appear in the scene. We present VAR-SLAM (Visual Adaptive and Robust SLAM), an ORB-SLAM3-based system that combines a lightweight semantic keypoint filter to deal with known moving objects, with Barron's adaptive robust loss to handle unknown ones. The shape parameter of the robust kernel is estimated online from residuals, allowing the system to automatically adjust between Gaussian and heavy-tailed behavior. We evaluate VAR-SLAM on the TUM RGB-D, Bonn RGB-D Dynamic, and OpenLORIS datasets, which include both known and unknown moving objects. Results show improved trajectory accuracy and robustness over state-of-the-art baselines, achieving up to 25% lower ATE RMSE than NGD-SLAM on challenging sequences, while maintaining performance at 27 FPS on average. |
Code ...Code available at https://github.com/iit-DLSLab/VAR-SLAM |
| LVI-Q: Robust LiDAR-Visual-Inertial-Kinematic Odometry for Quadruped Robots Using Tightly-Coupled and Efficient Alternating Optimization | 2025-10-17 | ShowAutonomous navigation for legged robots in complex and dynamic environments relies on robust simultaneous localization and mapping (SLAM) systems to accurately map surroundings and localize the robot, ensuring safe and efficient operation. While prior sensor fusion-based SLAM approaches have integrated various sensor modalities to improve their robustness, these algorithms are still susceptible to estimation drift in challenging environments due to their reliance on unsuitable fusion strategies. Therefore, we propose a robust LiDAR-visual-inertial-kinematic odometry system that integrates information from multiple sensors, such as a camera, LiDAR, inertial measurement unit (IMU), and joint encoders, for visual and LiDAR-based odometry estimation. Our system employs a fusion-based pose estimation approach that runs optimization-based visual-inertial-kinematic odometry (VIKO) and filter-based LiDAR-inertial-kinematic odometry (LIKO) based on measurement availability. In VIKO, we utilize the footpreintegration technique and robust LiDAR-visual depth consistency using superpixel clusters in a sliding window optimization. In LIKO, we incorporate foot kinematics and employ a point-toplane residual in an error-state iterative Kalman filter (ESIKF). Compared with other sensor fusion-based SLAM algorithms, our approach shows robust performance across public and longterm datasets. |
8 Pages, 9 Figures |
| Accelerated Feature Detectors for Visual SLAM: A Comparative Study of FPGA vs GPU | 2025-10-15 | ShowFeature detection is a common yet time-consuming module in Simultaneous Localization and Mapping (SLAM) implementations, which are increasingly deployed on power-constrained platforms, such as drones. Graphics Processing Units (GPUs) have been a popular accelerator for computer vision in general, and feature detection and SLAM in particular. On the other hand, System-on-Chips (SoCs) with integrated Field Programmable Gate Array (FPGA) are also widely available. This paper presents the first study of hardware-accelerated feature detectors considering a Visual SLAM (V-SLAM) pipeline. We offer new insights by comparing the best GPU-accelerated FAST, Harris, and SuperPoint implementations against the FPGA-accelerated counterparts on modern SoCs (Nvidia Jetson Orin and AMD Versal). The evaluation shows that when using a non-learning-based feature detector such as FAST and Harris, their GPU implementations, and the GPU-accelerated V-SLAM can achieve better run-time performance and energy efficiency than the FAST and Harris FPGA implementations as well as the FPGA-accelerated V-SLAM. However, when considering a learning-based detector such as SuperPoint, its FPGA implementation can achieve better run-time performance and energy efficiency (up to 3.1$\times$ and 1.4$\times$ improvements, respectively) than the GPU implementation. The FPGA-accelerated V-SLAM can also achieve comparable run-time performance compared to the GPU-accelerated V-SLAM, with better FPS in 2 out of 5 dataset sequences. When considering the accuracy, the results show that the GPU-accelerated V-SLAM is more accurate than the FPGA-accelerated V-SLAM in general. Last but not least, the use of hardware acceleration for feature detection could further improve the performance of the V-SLAM pipeline by having the global bundle adjustment module invoked less frequently without sacrificing accuracy. |
12 pages, 7 figures |
| Through the Lens of Doubt: Robust and Efficient Uncertainty Estimation for Visual Place Recognition | 2025-10-15 | ShowVisual Place Recognition (VPR) enables robots and autonomous vehicles to identify previously visited locations by matching current observations against a database of known places. However, VPR systems face significant challenges when deployed across varying visual environments, lighting conditions, seasonal changes, and viewpoints changes. Failure-critical VPR applications, such as loop closure detection in simultaneous localization and mapping (SLAM) pipelines, require robust estimation of place matching uncertainty. We propose three training-free uncertainty metrics that estimate prediction confidence by analyzing inherent statistical patterns in similarity scores from any existing VPR method. Similarity Distribution (SD) quantifies match distinctiveness by measuring score separation between candidates; Ratio Spread (RS) evaluates competitive ambiguity among top-scoring locations; and Statistical Uncertainty (SU) is a combination of SD and RS that provides a unified metric that generalizes across datasets and VPR methods without requiring validation data to select the optimal metric. All three metrics operate without additional model training, architectural modifications, or computationally expensive geometric verification. Comprehensive evaluation across nine state-of-the-art VPR methods and six benchmark datasets confirms that our metrics excel at discriminating between correct and incorrect VPR matches, and consistently outperform existing approaches while maintaining negligible computational overhead, making it deployable for real-time robotic applications across varied environmental conditions with improved precision-recall performance. |
|
| SMapper: A Multi-Modal Data Acquisition Platform for SLAM Benchmarking | 2025-10-10 | ShowAdvancing research in fields such as Simultaneous Localization and Mapping (SLAM) and autonomous navigation critically depends on the availability of reliable and reproducible multimodal datasets. While several influential datasets have driven progress in these domains, they often suffer from limitations in sensing modalities, environmental diversity, and the reproducibility of the underlying hardware setups. To address these challenges, this paper introduces SMapper, a novel open-hardware, multi-sensor platform designed explicitly for, though not limited to, SLAM research. The device integrates synchronized LiDAR, multi-camera, and inertial sensing, supported by a robust calibration and synchronization pipeline that ensures precise spatio-temporal alignment across modalities. Its open and replicable design allows researchers to extend its capabilities and reproduce experiments across both handheld and robot-mounted scenarios. To demonstrate its practicality, we additionally release SMapper-light, a publicly available SLAM dataset containing representative indoor and outdoor sequences. The dataset includes tightly synchronized multimodal data and ground truth trajectories derived from offline LiDAR-based SLAM with sub-centimeter accuracy, alongside dense 3D reconstructions. Furthermore, the paper contains benchmarking results on state-of-the-art LiDAR and visual SLAM frameworks using the SMapper-light dataset. By combining open-hardware design, reproducible data collection, and comprehensive benchmarking, SMapper establishes a robust foundation for advancing SLAM algorithm development, evaluation, and reproducibility. The project's documentation, including source code, CAD models, and dataset links, is publicly available at https://snt-arg.github.io/smapper_docs. |
13 pa...13 pages, 5 figures, 6 tables |
| ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representation | 2025-10-09 | ShowOn-the-fly 3D reconstruction from monocular image sequences is a long-standing challenge in computer vision, critical for applications such as real-to-sim, AR/VR, and robotics. Existing methods face a major tradeoff: per-scene optimization yields high fidelity but is computationally expensive, whereas feed-forward foundation models enable real-time inference but struggle with accuracy and robustness. In this work, we propose ARTDECO, a unified framework that combines the efficiency of feed-forward models with the reliability of SLAM-based pipelines. ARTDECO uses 3D foundation models for pose estimation and point prediction, coupled with a Gaussian decoder that transforms multi-scale features into structured 3D Gaussians. To sustain both fidelity and efficiency at scale, we design a hierarchical Gaussian representation with a LoD-aware rendering strategy, which improves rendering fidelity while reducing redundancy. Experiments on eight diverse indoor and outdoor benchmarks show that ARTDECO delivers interactive performance comparable to SLAM, robustness similar to feed-forward systems, and reconstruction quality close to per-scene optimization, providing a practical path toward on-the-fly digitization of real-world environments with both accurate geometry and high visual fidelity. Explore more demos on our project page: https://city-super.github.io/artdeco/. |
|
| SiLVR: Scalable Lidar-Visual Radiance Field Reconstruction with Uncertainty Quantification | 2025-10-08 | ShowWe present a neural radiance field (NeRF) based large-scale reconstruction system that fuses lidar and vision data to generate high-quality reconstructions that are geometrically accurate and capture photorealistic texture. Our system adopts the state-of-the-art NeRF representation to incorporate lidar. Adding lidar data adds strong geometric constraints on the depth and surface normals, which is particularly useful when modelling uniform texture surfaces which contain ambiguous visual reconstruction cues. A key contribution of this work is a novel method to quantify the epistemic uncertainty of the lidar-visual NeRF reconstruction by estimating the spatial variance of each point location in the radiance field given the sensor observations from the cameras and lidar. This provides a principled approach to evaluate the contribution of each sensor modality to the final reconstruction. In this way, reconstructions that are uncertain (due to e.g. uniform visual texture, limited observation viewpoints, or little lidar coverage) can be identified and removed. Our system is integrated with a real-time lidar SLAM system which is used to bootstrap a Structure-from-Motion (SfM) reconstruction procedure. It also helps to properly constrain the overall metric scale which is essential for the lidar depth loss. The refined SLAM trajectory can then be divided into submaps using Spectral Clustering to group sets of co-visible images together. This submapping approach is more suitable for visual reconstruction than distance-based partitioning. Our uncertainty estimation is particularly effective when merging submaps as their boundaries often contain artefacts due to limited observations. We demonstrate the reconstruction system using a multi-camera, lidar sensor suite in experiments involving both robot-mounted and handheld scanning. Our test datasets cover a total area of more than 20,000 square metres. |
Accep...Accepted by T-RO. Webpage: https://dynamic.robots.ox.ac.uk/projects/silvr/ |
| EgoExo++: Integrating On-demand Exocentric Visuals with 2.5D Ground Surface Estimation for Interactive Teleoperation of Subsea ROVs | 2025-10-08 | ShowUnderwater ROVs (Remotely Operated Vehicles) are indispensable for subsea exploration and task execution, yet typical teleoperation engines based on egocentric (first-person) video feeds restrict human operators' field-of-view and limit precise maneuvering in complex, unstructured underwater environments. To address this, we propose EgoExo, a geometry-driven solution integrated into a visual SLAM pipeline that synthesizes on-demand exocentric (third-person) views from egocentric camera feeds. Our proposed framework, EgoExo++, extends beyond 2D exocentric view synthesis (EgoExo) to augment a dense 2.5D ground surface estimation on-the-fly. It simultaneously renders the ROV model onto this reconstructed surface, enhancing semantic perception and depth comprehension. The computations involved are closed-form and rely solely on egocentric views and monocular SLAM estimates, which makes it portable across existing teleoperation engines and robust to varying waterbody characteristics. We validate the geometric accuracy of our approach through extensive experiments of 2-DOF indoor navigation and 6-DOF underwater cave exploration in challenging low-light conditions. Quantitative metrics confirm the reliability of the rendered Exo views, while a user study involving 15 operators demonstrates improved situational awareness, navigation safety, and task efficiency during teleoperation. Furthermore, we highlight the role of EgoExo++ augmented visuals in supporting shared autonomy, operator training, and embodied teleoperation. This new interactive approach to ROV teleoperation presents promising opportunities for future research in subsea telerobotics. |
EgoEx...EgoExo++ (Journal extension), V5, metadata updated, 12 pages |
| BIM-Constrained Optimization for Accurate Localization and Deviation Correction in Construction Monitoring | 2025-10-08 | ShowAugmented reality (AR) applications for construction monitoring rely on real-time environmental tracking to visualize architectural elements. However, construction sites present significant challenges for traditional tracking methods due to featureless surfaces, dynamic changes, and drift accumulation, leading to misalignment between digital models and the physical world. This paper proposes a BIM-aware drift correction method to address these challenges. Instead of relying solely on SLAM-based localization, we align |
|
| BIM Informed Visual SLAM for Construction Monitoring | 2025-10-08 | ShowSimultaneous Localization and Mapping (SLAM) is a key tool for monitoring construction sites, where aligning the evolving as-built state with the as-planned design enables early error detection and reduces costly rework. LiDAR-based SLAM achieves high geometric precision, but its sensors are typically large and power-demanding, limiting their use on portable platforms. Visual SLAM offers a practical alternative with lightweight cameras already embedded in most mobile devices. however, visually mapping construction environments remains challenging: repetitive layouts, occlusions, and incomplete or low-texture structures often cause drift in the trajectory map. To mitigate this, we propose an RGB-D SLAM system that incorporates the Building Information Model (BIM) as structural prior knowledge. Instead of relying solely on visual cues, our system continuously establishes correspondences between detected wall and their BIM counterparts, which are then introduced as constraints in the back-end optimization. The proposed method operates in real time and has been validated on real construction sites, reducing trajectory error by an average of 23.71% and map RMSE by 7.14% compared to visual SLAM baselines. These results demonstrate that BIM constraints enable reliable alignment of the digital plan with the as-built scene, even under partially constructed conditions. |
8 pag...8 pages, 5 tables, 4 figures |
| Human3R: Everyone Everywhere All at Once | 2025-10-07 | ShowWe present Human3R, a unified, feed-forward framework for online 4D human-scene reconstruction, in the world frame, from casually captured monocular videos. Unlike previous approaches that rely on multi-stage pipelines, iterative contact-aware refinement between humans and scenes, and heavy dependencies, e.g., human detection, depth estimation, and SLAM pre-processing, Human3R jointly recovers global multi-person SMPL-X bodies ("everyone"), dense 3D scene ("everywhere"), and camera trajectories in a single forward pass ("all-at-once"). Our method builds upon the 4D online reconstruction model CUT3R, and uses parameter-efficient visual prompt tuning, to strive to preserve CUT3R's rich spatiotemporal priors, while enabling direct readout of multiple SMPL-X bodies. Human3R is a unified model that eliminates heavy dependencies and iterative refinement. After being trained on the relatively small-scale synthetic dataset BEDLAM for just one day on one GPU, it achieves superior performance with remarkable efficiency: it reconstructs multiple humans in a one-shot manner, along with 3D scenes, in one stage, at real-time speed (15 FPS) with a low memory footprint (8 GB). Extensive experiments demonstrate that Human3R delivers state-of-the-art or competitive performance across tasks, including global human motion estimation, local human mesh recovery, video depth estimation, and camera pose estimation, with a single unified model. We hope that Human3R will serve as a simple yet strong baseline, be easily extended for downstream applications.Code available in https://fanegg.github.io/Human3R |
Page:...Page: https://fanegg.github.io/Human3R Code: https://github.com/fanegg/Human3R |
| OKVIS2-X: Open Keyframe-based Visual-Inertial SLAM Configurable with Dense Depth or LiDAR, and GNSS | 2025-10-06 | ShowTo empower mobile robots with usable maps as well as highest state estimation accuracy and robustness, we present OKVIS2-X: a state-of-the-art multi-sensor Simultaneous Localization and Mapping (SLAM) system building dense volumetric occupancy maps, while scalable to large environments and operating in realtime. Our unified SLAM framework seamlessly integrates different sensor modalities: visual, inertial, measured or learned depth, LiDAR and Global Navigation Satellite System (GNSS) measurements. Unlike most state-of-the-art SLAM systems, we advocate using dense volumetric map representations when leveraging depth or range-sensing capabilities. We employ an efficient submapping strategy that allows our system to scale to large environments, showcased in sequences of up to 9 kilometers. OKVIS2-X enhances its accuracy and robustness by tightly-coupling the estimator and submaps through map alignment factors. Our system provides globally consistent maps, directly usable for autonomous navigation. To further improve the accuracy of OKVIS2-X, we also incorporate the option of performing online calibration of camera extrinsics. Our system achieves the highest trajectory accuracy in EuRoC against state-of-the-art alternatives, outperforms all competitors in the Hilti22 VI-only benchmark, while also proving competitive in the LiDAR version, and showcases state of the art accuracy in the diverse and large-scale sequences from the VBR dataset. |
IEEE ...IEEE Transactions on Robotics (T-RO) - Special Issue: Visual SLAM |
| RSV-SLAM: Toward Real-Time Semantic Visual SLAM in Indoor Dynamic Environments | 2025-10-02 | ShowSimultaneous Localization and Mapping (SLAM) plays an important role in many robotics fields, including social robots. Many of the available visual SLAM methods are based on the assumption of a static world and struggle in dynamic environments. In the current study, we introduce a real-time semantic RGBD SLAM approach designed specifically for dynamic environments. Our proposed system can effectively detect moving objects and maintain a static map to ensure robust camera tracking. The key innovation of our approach is the incorporation of deep learning-based semantic information into SLAM systems to mitigate the impact of dynamic objects. Additionally, we enhance the semantic segmentation process by integrating an Extended Kalman filter to identify dynamic objects that may be temporarily idle. We have also implemented a generative network to fill in the missing regions of input images belonging to dynamic objects. This highly modular framework has been implemented on the ROS platform and can achieve around 22 fps on a GTX1080. Benchmarking the developed pipeline on dynamic sequences from the TUM dataset suggests that the proposed approach delivers competitive localization error in comparison with the state-of-the-art methods, all while operating in near real-time. The source code is publicly available. |
Proce...Proceedings of SAI Intelligent Systems Conference 2023 |
| Non-Rigid Structure-from-Motion via Differential Geometry with Recoverable Conformal Scale | 2025-10-02 | ShowNon-rigid structure-from-motion (NRSfM), a promising technique for addressing the mapping challenges in monocular visual deformable simultaneous localization and mapping (SLAM), has attracted growing attention. We introduce a novel method, called Con-NRSfM, for NRSfM under conformal deformations, encompassing isometric deformations as a subset. Our approach performs point-wise reconstruction using 2D selected image warps optimized through a graph-based framework. Unlike existing methods that rely on strict assumptions, such as locally planar surfaces or locally linear deformations, and fail to recover the conformal scale, our method eliminates these constraints and accurately computes the local conformal scale. Additionally, our framework decouples constraints on depth and conformal scale, which are inseparable in other approaches, enabling more precise depth estimation. To address the sensitivity of the formulated problem, we employ a parallel separable iterative optimization strategy. Furthermore, a self-supervised learning framework, utilizing an encoder-decoder network, is incorporated to generate dense 3D point clouds with texture. Simulation and experimental results using both synthetic and real datasets demonstrate that our method surpasses existing approaches in terms of reconstruction accuracy and robustness. The code for the proposed method will be made publicly available on the project website: https://sites.google.com/view/con-nrsfm. |
|
| Instant4D: 4D Gaussian Splatting in Minutes | 2025-10-01 | ShowDynamic view synthesis has seen significant advances, yet reconstructing scenes from uncalibrated, casual video remains challenging due to slow optimization and complex parameter estimation. In this work, we present Instant4D, a monocular reconstruction system that leverages native 4D representation to efficiently process casual video sequences within minutes, without calibrated cameras or depth sensors. Our method begins with geometric recovery through deep visual SLAM, followed by grid pruning to optimize scene representation. Our design significantly reduces redundancy while maintaining geometric integrity, cutting model size to under 10% of its original footprint. To handle temporal dynamics efficiently, we introduce a streamlined 4D Gaussian representation, achieving a 30x speed-up and reducing training time to within two minutes, while maintaining competitive performance across several benchmarks. Our method reconstruct a single video within 10 minutes on the Dycheck dataset or for a typical 200-frame video. We further apply our model to in-the-wild videos, showcasing its generalizability. Our project website is published at https://instant4d.github.io/. |
Accep...Accepted by NeurIPS 25 |
| Semantic Visual Simultaneous Localization and Mapping: A Survey on State of the Art, Challenges, and Future Directions | 2025-10-01 | ShowSemantic Simultaneous Localization and Mapping (SLAM) is a critical area of research within robotics and computer vision, focusing on the simultaneous localization of robotic systems and associating semantic information to construct the most accurate and complete comprehensive model of the surrounding environment. Since the first foundational work in Semantic SLAM appeared more than two decades ago, this field has received increasing attention across various scientific communities. Despite its significance, the field lacks comprehensive surveys encompassing recent advances and persistent challenges. In response, this study provides a thorough examination of the state-of-the-art of Semantic SLAM techniques, with the aim of illuminating current trends and key obstacles. Beginning with an in-depth exploration of the evolution of visual SLAM, this study outlines its strengths and unique characteristics, while also critically assessing previous survey literature. Subsequently, a unified problem formulation and evaluation of the modular solution framework is proposed, which divides the problem into discrete stages, including visual localization, semantic feature extraction, mapping, data association, and loop closure optimization. Moreover, this study investigates alternative methodologies such as deep learning and the utilization of large language models, alongside a review of relevant research about contemporary SLAM datasets. Concluding with a discussion on potential future research directions, this study serves as a comprehensive resource for researchers seeking to navigate the complex landscape of Semantic SLAM. |
|
| Benchmarking Egocentric Visual-Inertial SLAM at City Scale | 2025-09-30 | ShowPrecise 6-DoF simultaneous localization and mapping (SLAM) from onboard sensors is critical for wearable devices capturing egocentric data, which exhibits specific challenges, such as a wider diversity of motions and viewpoints, prevalent dynamic visual content, or long sessions affected by time-varying sensor calibration. While recent progress on SLAM has been swift, academic research is still driven by benchmarks that do not reflect these challenges or do not offer sufficiently accurate ground truth poses. In this paper, we introduce a new dataset and benchmark for visual-inertial SLAM with egocentric, multi-modal data. We record hours and kilometers of trajectories through a city center with glasses-like devices equipped with various sensors. We leverage surveying tools to obtain control points as indirect pose annotations that are metric, centimeter-accurate, and available at city scale. This makes it possible to evaluate extreme trajectories that involve walking at night or traveling in a vehicle. We show that state-of-the-art systems developed by academia are not robust to these challenges and we identify components that are responsible for this. In addition, we design tracks with different levels of difficulty to ease in-depth analysis and evaluation of less mature approaches. The dataset and benchmark are available at https://www.lamaria.ethz.ch. |
ICCV 2025 |
| Graphite: A GPU-Accelerated Mixed-Precision Graph Optimization Framework | 2025-09-30 | ShowWe present Graphite, a GPU-accelerated nonlinear graph optimization framework. It provides a CUDA C++ interface to enable the sharing of code between a realtime application, such as a SLAM system, and its optimization tasks. The framework supports techniques to reduce memory usage, including in-place optimization, support for multiple floating point types and mixed-precision modes, and dynamically computed Jacobians. We evaluate Graphite on well-known bundle adjustment problems and find that it achieves similar performance to MegBA, a solver specialized for bundle adjustment, while maintaining generality and using less memory. We also apply Graphite to global visual-inertial bundle adjustment on maps generated from stereo-inertial SLAM datasets, and observe speed ups of up to 59x compared to a CPU baseline. Our results indicate that our solver enables faster large-scale optimization on both desktop and resource-constrained devices. |
|
| SuperEvent: Cross-Modal Learning of Event-based Keypoint Detection for SLAM | 2025-09-29 | ShowEvent-based keypoint detection and matching holds significant potential, enabling the integration of event sensors into highly optimized Visual SLAM systems developed for frame cameras over decades of research. Unfortunately, existing approaches struggle with the motion-dependent appearance of keypoints and the complex noise prevalent in event streams, resulting in severely limited feature matching capabilities and poor performance on downstream tasks. To mitigate this problem, we propose SuperEvent, a data-driven approach to predict stable keypoints with expressive descriptors. Due to the absence of event datasets with ground truth keypoint labels, we leverage existing frame-based keypoint detectors on readily available event-aligned and synchronized gray-scale frames for self-supervision: we generate temporally sparse keypoint pseudo-labels considering that events are a product of both scene appearance and camera motion. Combined with our novel, information-rich event representation, we enable SuperEvent to effectively learn robust keypoint detection and description in event streams. Finally, we demonstrate the usefulness of SuperEvent by its integration into a modern sparse keypoint and descriptor-based SLAM framework originally developed for traditional cameras, surpassing the state-of-the-art in event-based SLAM by a wide margin. Source code is available at https://ethz-mrl.github.io/SuperEvent/. |
|
| Self-Supervised Geometry-Guided Initialization for Robust Monocular Visual Odometry | 2025-09-28 | ShowMonocular visual odometry is a key technology in various autonomous systems. Traditional feature-based methods suffer from failures due to poor lighting, insufficient texture, and large motions. In contrast, recent learning-based dense SLAM methods exploit iterative dense bundle adjustment to address such failure cases, and achieve robust and accurate localization in a wide variety of real environments, without depending on domain-specific supervision. However, despite its potential, the methods still struggle with scenarios involving large motion and object dynamics. In this study, we diagnose key weaknesses in a popular learning-based dense SLAM model (DROID-SLAM) by analyzing major failure cases on outdoor benchmarks and exposing various shortcomings of its optimization process. We then propose the use of self-supervised priors leveraging a frozen large-scale pre-trained monocular depth estimator to initialize the dense bundle adjustment process, leading to robust visual odometry without the need to fine-tune the SLAM backbone. Despite its simplicity, the proposed method demonstrates significant improvements on KITTI odometry, as well as the challenging DDAD benchmark. |
Proje...Project page: https://toyotafrc.github.io/SGInit-Proj/ |
| GRS-SLAM3R: Real-Time Dense SLAM with Gated Recurrent State | 2025-09-28 | ShowDUSt3R-based end-to-end scene reconstruction has recently shown promising results in dense visual SLAM. However, most existing methods only use image pairs to estimate pointmaps, overlooking spatial memory and global consistency.To this end, we introduce GRS-SLAM3R, an end-to-end SLAM framework for dense scene reconstruction and pose estimation from RGB images without any prior knowledge of the scene or camera parameters. Unlike existing DUSt3R-based frameworks, which operate on all image pairs and predict per-pair point maps in local coordinate frames, our method supports sequentialized input and incrementally estimates metric-scale point clouds in the global coordinate. In order to improve consistent spatial correlation, we use a latent state for spatial memory and design a transformer-based gated update module to reset and update the spatial memory that continuously aggregates and tracks relevant 3D information across frames. Furthermore, we partition the scene into submaps, apply local alignment within each submap, and register all submaps into a common world frame using relative constraints, producing a globally consistent map. Experiments on various datasets show that our framework achieves superior reconstruction accuracy while maintaining real-time performance. |
|
| Good Weights: Proactive, Adaptive Dead Reckoning Fusion for Continuous and Robust Visual SLAM | 2025-09-26 | ShowGiven that Visual SLAM relies on appearance cues for localization and scene understanding, texture-less or visually degraded environments (e.g., plain walls or low lighting) lead to poor pose estimation and track loss. However, robots are typically equipped with sensors that provide some form of dead reckoning odometry with reasonable short-time performance but unreliable long-time performance. The Good Weights (GW) algorithm described here provides a framework to adaptively integrate dead reckoning (DR) with passive visual SLAM for continuous and accurate frame-level pose estimation. Importantly, it describes how all modules in a comprehensive SLAM system must be modified to incorporate DR into its design. Adaptive weighting increases DR influence when visual tracking is unreliable and reduces when visual feature information is strong, maintaining pose track without overreliance on DR. Good Weights yields a practical solution for mobile navigation that improves visual SLAM performance and robustness. Experiments on collected datasets and in real-world deployment demonstrate the benefits of Good Weights. |
8 pag...8 pages, 9 figures, 1 table. Submitted to IEEE Conference |
| AnywhereVLA: Language-Conditioned Exploration and Mobile Manipulation | 2025-09-25 | ShowWe address natural language pick-and-place in unseen, unpredictable indoor environments with AnywhereVLA, a modular framework for mobile manipulation. A user text prompt serves as an entry point and is parsed into a structured task graph that conditions classical SLAM with LiDAR and cameras, metric semantic mapping, and a task-aware frontier exploration policy. An approach planner then selects visibility and reachability aware pre grasp base poses. For interaction, a compact SmolVLA manipulation head is fine tuned on platform pick and place trajectories for the SO-101 by TheRobotStudio, grounding local visual context and sub-goals into grasp and place proposals. The full system runs fully onboard on consumer-level hardware, with Jetson Orin NX for perception and VLA and an Intel NUC for SLAM, exploration, and control, sustaining real-time operation. We evaluated AnywhereVLA in a multi-room lab under static scenes and normal human motion. In this setting, the system achieves a |
|
| SLAM-Free Visual Navigation with Hierarchical Vision-Language Perception and Coarse-to-Fine Semantic Topological Planning | 2025-09-25 | ShowConventional SLAM pipelines for legged robot navigation are fragile under rapid motion, calibration demands, and sensor drift, while offering limited semantic reasoning for task-driven exploration. To deal with these issues, we propose a vision-only, SLAM-free navigation framework that replaces dense geometry with semantic reasoning and lightweight topological representations. A hierarchical vision-language perception module fuses scene-level context with object-level cues for robust semantic inference. And a semantic-probabilistic topological map supports coarse-to-fine planning: LLM-based global reasoning for subgoal selection and vision-based local planning for obstacle avoidance. Integrated with reinforcement-learning locomotion controllers, the framework is deployable across diverse legged robot platforms. Experiments in simulation and real-world settings demonstrate consistent improvements in semantic accuracy, planning quality, and navigation success, while ablation studies further showcase the necessity of both hierarchical perception and fine local planning. This work introduces a new paradigm for SLAM-free, vision-language-driven navigation, shifting robotic exploration from geometry-centric mapping to semantics-driven decision making. |
|
| Optical Ocean Recipes: Creating Realistic Datasets to Facilitate Underwater Vision Research | 2025-09-24 | ShowThe development and evaluation of machine vision in underwater environments remains challenging, often relying on trial-and-error-based testing tailored to specific applications. This is partly due to the lack of controlled, ground-truthed testing environments that account for the optical challenges, such as color distortion from spectrally variant light attenuation, reduced contrast and blur from backscatter and volume scattering, and dynamic light patterns from natural or artificial illumination. Additionally, the appearance of ocean water in images varies significantly across regions, depths, and seasons. However, most machine vision evaluations are conducted under specific optical water types and imaging conditions, therefore often lack generalizability. Exhaustive testing across diverse open-water scenarios is technically impractical. To address this, we introduce the \textit{Optical Ocean Recipes}, a framework for creating realistic datasets under controlled underwater conditions. Unlike synthetic or open-water data, these recipes, using calibrated color and scattering additives, enable repeatable and controlled testing of the impact of water composition on image appearance. Hence, this provides a unique framework for analyzing machine vision in realistic, yet controlled underwater scenarios. The controlled environment enables the creation of ground-truth data for a range of vision tasks, including water parameter estimation, image restoration, segmentation, visual SLAM, and underwater image synthesis. We provide a demonstration dataset generated using the Optical Ocean Recipes and briefly demonstrate the use of our system for two underwater vision tasks. The dataset and evaluation code will be made available. |
26 pa...26 pages, 9 figures, submitted to IEEE Journal of Ocean Engineering |
| Bioinspired SLAM Approach for Unmanned Surface Vehicle | 2025-09-23 | ShowThis paper presents OpenRatSLAM2, a new version of OpenRatSLAM - a bioinspired SLAM framework based on computational models of the rodent hippocampus. OpenRatSLAM2 delivers low-computation-cost visual-inertial based SLAM, suitable for GPS-denied environments. Our contributions include a ROS2-based architecture, experimental results on new waterway datasets, and insights into system parameter tuning. This work represents the first known application of RatSLAM on USVs. The estimated trajectory was compared with ground truth data using the Hausdorff distance. The results show that the algorithm can generate a semimetric map with an error margin acceptable for most robotic applications. |
|
| ConfidentSplat: Confidence-Weighted Depth Fusion for Accurate 3D Gaussian Splatting SLAM | 2025-09-21 | ShowWe introduce ConfidentSplat, a novel 3D Gaussian Splatting (3DGS)-based SLAM system for robust, highfidelity RGB-only reconstruction. Addressing geometric inaccuracies in existing RGB-only 3DGS SLAM methods that stem from unreliable depth estimation, ConfidentSplat incorporates a core innovation: a confidence-weighted fusion mechanism. This mechanism adaptively integrates depth cues from multiview geometry with learned monocular priors (Omnidata ViT), dynamically weighting their contributions based on explicit reliability estimates-derived predominantly from multi-view geometric consistency-to generate high-fidelity proxy depth for map supervision. The resulting proxy depth guides the optimization of a deformable 3DGS map, which efficiently adapts online to maintain global consistency following pose updates from a DROID-SLAM-inspired frontend and backend optimizations (loop closure, global bundle adjustment). Extensive validation on standard benchmarks (TUM-RGBD, ScanNet) and diverse custom mobile datasets demonstrates significant improvements in reconstruction accuracy (L1 depth error) and novel view synthesis fidelity (PSNR, SSIM, LPIPS) over baselines, particularly in challenging conditions. ConfidentSplat underscores the efficacy of principled, confidence-aware sensor fusion for advancing state-of-the-art dense visual SLAM. |
|
| NFL-BA: Near-Field Light Bundle Adjustment for SLAM in Dynamic Lighting | 2025-09-18 | ShowSimultaneous Localization and Mapping (SLAM) systems typically assume static, distant illumination; however, many real-world scenarios, such as endoscopy, subterranean robotics, and search & rescue in collapsed environments, require agents to operate with a co-located light and camera in the absence of external lighting. In such cases, dynamic near-field lighting introduces strong, view-dependent shading that significantly degrades SLAM performance. We introduce Near-Field Lighting Bundle Adjustment Loss (NFL-BA) which explicitly models near-field lighting as a part of Bundle Adjustment loss and enables better performance for scenes captured with dynamic lighting. NFL-BA can be integrated into neural rendering-based SLAM systems with implicit or explicit scene representations. Our evaluations mainly focus on endoscopy procedure where SLAM can enable autonomous navigation, guidance to unsurveyed regions, blindspot detections, and 3D visualizations, which can significantly improve patient outcomes and endoscopy experience for both physicians and patients. Replacing Photometric Bundle Adjustment loss of SLAM systems with NFL-BA leads to significant improvement in camera tracking, 37% for MonoGS and 14% for EndoGS, and leads to state-of-the-art camera tracking and mapping performance on the C3VD colonoscopy dataset. Further evaluation on indoor scenes captured with phone camera with flashlight turned on, also demonstrate significant improvement in SLAM performance due to NFL-BA. See results at https://asdunnbe.github.io/NFL-BA/ |
|
| Human Interaction for Collaborative Semantic SLAM using Extended Reality | 2025-09-18 | ShowSemantic SLAM (Simultaneous Localization and Mapping) systems enrich robot maps with structural and semantic information, enabling robots to operate more effectively in complex environments. However, these systems struggle in real-world scenarios with occlusions, incomplete data, or ambiguous geometries, as they cannot fully leverage the higher-level spatial and semantic knowledge humans naturally apply. We introduce HICS-SLAM, a Human-in-the-Loop semantic SLAM framework that uses a shared extended reality environment for real-time collaboration. The system allows human operators to directly interact with and visualize the robot's 3D scene graph, and add high-level semantic concepts (e.g., rooms or structural entities) into the mapping process. We propose a graph-based semantic fusion methodology that integrates these human interventions with robot perception, enabling scalable collaboration for enhanced situational awareness. Experimental evaluations on real-world construction site datasets demonstrate improvements in room detection accuracy, map precision, and semantic completeness compared to automated baselines, demonstrating both the effectiveness of the approach and its potential for future extensions. |
7 pag...7 pages, 5 figures, 3 tables |
| Event-LAB: Towards Standardized Evaluation of Neuromorphic Localization Methods | 2025-09-18 | ShowEvent-based localization research and datasets are a rapidly growing area of interest, with a tenfold increase in the cumulative total number of published papers on this topic over the past 10 years. Whilst the rapid expansion in the field is exciting, it brings with it an associated challenge: a growth in the variety of required code and package dependencies as well as data formats, making comparisons difficult and cumbersome for researchers to implement reliably. To address this challenge, we present Event-LAB: a new and unified framework for running several event-based localization methodologies across multiple datasets. Event-LAB is implemented using the Pixi package and dependency manager, that enables a single command-line installation and invocation for combinations of localization methods and datasets. To demonstrate the capabilities of the framework, we implement two common event-based localization pipelines: Visual Place Recognition (VPR) and Simultaneous Localization and Mapping (SLAM). We demonstrate the ability of the framework to systematically visualize and analyze the results of multiple methods and datasets, revealing key insights such as the association of parameters that control event collection counts and window sizes for frame generation to large variations in performance. The results and analysis demonstrate the importance of fairly comparing methodologies with consistent event image generation parameters. Our Event-LAB framework provides this ability for the research community, by contributing a streamlined workflow for easily setting up multiple conditions. |
8 pag...8 pages, 6 figures, under review |
| See What I Mean? Mobile Eye-Perspective Rendering for Optical See-through Head-mounted Displays | 2025-09-15 | ShowImage-based scene understanding allows Augmented Reality systems to provide contextual visual guidance in unprepared, real-world environments. While effective on video see-through (VST) head-mounted displays (HMDs), such methods suffer on optical see-through (OST) HMDs due to misregistration between the world-facing camera and the user's eye perspective. To approximate the user's true eye view, we implement and evaluate three software-based eye-perspective rendering (EPR) techniques on a commercially available, untethered OST HMD (Microsoft HoloLens 2): (1) Plane-Proxy EPR, projecting onto a fixed-distance plane; (2) Mesh-Proxy EPR, using SLAM-based reconstruction for projection; and (3) Gaze-Proxy EPR, a novel eye-tracking-based method that aligns the projection with the user's gaze depth. A user study on real-world tasks underscores the importance of accurate EPR and demonstrates gaze-proxy as a lightweight alternative to geometry-based methods. We release our EPR framework as open source. |
|
| Real-time Photorealistic Mapping for Situational Awareness in Robot Teleoperation | 2025-09-15 | ShowAchieving efficient remote teleoperation is particularly challenging in unknown environments, as the teleoperator must rapidly build an understanding of the site's layout. Online 3D mapping is a proven strategy to tackle this challenge, as it enables the teleoperator to progressively explore the site from multiple perspectives. However, traditional online map-based teleoperation systems struggle to generate visually accurate 3D maps in real-time due to the high computational cost involved, leading to poor teleoperation performances. In this work, we propose a solution to improve teleoperation efficiency in unknown environments. Our approach proposes a novel, modular and efficient GPU-based integration between recent advancement in gaussian splatting SLAM and existing online map-based teleoperation systems. We compare the proposed solution against state-of-the-art teleoperation systems and validate its performances through real-world experiments using an aerial vehicle. The results show significant improvements in decision-making speed and more accurate interaction with the environment, leading to greater teleoperation efficiency. In doing so, our system enhances remote teleoperation by seamlessly integrating photorealistic mapping generation with real-time performances, enabling effective teleoperation in unfamiliar environments. |
|
| FastTrack: GPU-Accelerated Tracking for Visual SLAM | 2025-09-13 | ShowThe tracking module of a visual-inertial SLAM system processes incoming image frames and IMU data to estimate the position of the frame in relation to the map. It is important for the tracking to complete in a timely manner for each frame to avoid poor localization or tracking loss. We therefore present a new approach which leverages GPU computing power to accelerate time-consuming components of tracking in order to improve its performance. These components include stereo feature matching and local map tracking. We implement our design inside the ORB-SLAM3 tracking process using CUDA. Our evaluation demonstrates an overall improvement in tracking performance of up to 2.8x on a desktop and Jetson Xavier NX board in stereo-inertial mode, using the well-known SLAM datasets EuRoC and TUM-VI. |
Accep...Accepted for presentation at IROS 2025, preprint |
| The Oxford Spires Dataset: Benchmarking Large-Scale LiDAR-Visual Localisation, Reconstruction and Radiance Field Methods | 2025-09-10 | ShowThis paper introduces a large-scale multi-modal dataset captured in and around well-known landmarks in Oxford using a custom-built multi-sensor perception unit as well as a millimetre-accurate map from a Terrestrial LiDAR Scanner (TLS). The perception unit includes three synchronised global shutter colour cameras, an automotive 3D LiDAR scanner, and an inertial sensor - all precisely calibrated. We also establish benchmarks for tasks involving localisation, reconstruction, and novel-view synthesis, which enable the evaluation of Simultaneous Localisation and Mapping (SLAM) methods, Structure-from-Motion (SfM) and Multi-view Stereo (MVS) methods as well as radiance field methods such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting. To evaluate 3D reconstruction the TLS 3D models are used as ground truth. Localisation ground truth is computed by registering the mobile LiDAR scans to the TLS 3D models. Radiance field methods are evaluated not only with poses sampled from the input trajectory, but also from viewpoints that are from trajectories which are distant from the training poses. Our evaluation demonstrates a key limitation of state-of-the-art radiance field methods: we show that they tend to overfit to the training poses/images and do not generalise well to out-of-sequence poses. They also underperform in 3D reconstruction compared to MVS systems using the same visual inputs. Our dataset and benchmarks are intended to facilitate better integration of radiance field methods and SLAM systems. The raw and processed data, along with software for parsing and evaluation, can be accessed at https://dynamic.robots.ox.ac.uk/datasets/oxford-spires/. |
Accep...Accepted by IJRR. Website: https://dynamic.robots.ox.ac.uk/datasets/oxford-spires/ |
| PINGS: Gaussian Splatting Meets Distance Fields within a Point-Based Implicit Neural Map | 2025-09-09 | ShowRobots benefit from high-fidelity reconstructions of their environment, which should be geometrically accurate and photorealistic to support downstream tasks. While this can be achieved by building distance fields from range sensors and radiance fields from cameras, realising scalable incremental mapping of both fields consistently and at the same time with high quality is challenging. In this paper, we propose a novel map representation that unifies a continuous signed distance field and a Gaussian splatting radiance field within an elastic and compact point-based implicit neural map. By enforcing geometric consistency between these fields, we achieve mutual improvements by exploiting both modalities. We present a novel LiDAR-visual SLAM system called PINGS using the proposed map representation and evaluate it on several challenging large-scale datasets. Experimental results demonstrate that PINGS can incrementally build globally consistent distance and radiance fields encoded with a compact set of neural points. Compared to state-of-the-art methods, PINGS achieves superior photometric and geometric rendering at novel views by constraining the radiance field with the distance field. Furthermore, by utilizing dense photometric cues and multi-view consistency from the radiance field, PINGS produces more accurate distance fields, leading to improved odometry estimation and mesh reconstruction. We also provide an open-source implementation of PING at: https://github.com/PRBonn/PINGS. |
15 pa...15 pages, 8 figures, presented at RSS 2025 |
| ESVO2: Direct Visual-Inertial Odometry with Stereo Event Cameras | 2025-09-08 | ShowEvent-based visual odometry is a specific branch of visual Simultaneous Localization and Mapping (SLAM) techniques, which aims at solving tracking and mapping subproblems (typically in parallel), by exploiting the special working principles of neuromorphic (i.e., event-based) cameras. Due to the motion-dependent nature of event data, explicit data association (i.e., feature matching) under large-baseline view-point changes is difficult to establish, making direct methods a more rational choice. However, state-of-the-art direct methods are limited by the high computational complexity of the mapping sub-problem and the degeneracy of camera pose tracking in certain degrees of freedom (DoF) in rotation. In this paper, we tackle these issues by building an event-based stereo visual-inertial odometry system on top of a direct pipeline. Specifically, to speed up the mapping operation, we propose an efficient strategy for sampling contour points according to the local dynamics of events. The mapping performance is also improved in terms of structure completeness and local smoothness by merging the temporal stereo and static stereo results. To circumvent the degeneracy of camera pose tracking in recovering the pitch and yaw components of general 6-DoF motion, we introduce IMU measurements as motion priors via pre-integration. To this end, a compact back-end is proposed for continuously updating the IMU bias and predicting the linear velocity, enabling an accurate motion prediction for camera pose tracking. The resulting system scales well with modern high-resolution event cameras and leads to better global positioning accuracy in large-scale outdoor environments. Extensive evaluations on five publicly available datasets featuring different resolutions and scenarios justify the superior performance of the proposed system against five state-of-the-art methods. |
|
| Active Illumination for Visual Ego-Motion Estimation in the Dark | 2025-09-08 | ShowVisual Odometry (VO) and Visual SLAM (V-SLAM) systems often struggle in low-light and dark environments due to the lack of robust visual features. In this paper, we propose a novel active illumination framework to enhance the performance of VO and V-SLAM algorithms in these challenging conditions. The developed approach dynamically controls a moving light source to illuminate highly textured areas, thereby improving feature extraction and tracking. Specifically, a detector block, which incorporates a deep learning-based enhancing network, identifies regions with relevant features. Then, a pan-tilt controller is responsible for guiding the light beam toward these areas, so that to provide information-rich images to the ego-motion estimation algorithm. Experimental results on a real robotic platform demonstrate the effectiveness of the proposed method, showing a reduction in the pose estimation error up to 75% with respect to a traditional fixed lighting technique. |
|
| 3D Densification for Multi-Map Monocular VSLAM in Endoscopy | 2025-09-05 | ShowMulti-map Sparse Monocular visual Simultaneous Localization and Mapping applied to monocular endoscopic sequences has proven efficient to robustly recover tracking after the frequent losses in endoscopy due to motion blur, temporal occlusion, tools interaction or water jets. The sparse multi-maps are adequate for robust camera localization, however they are very poor for environment representation, they are noisy, with a high percentage of inaccurately reconstructed 3D points, including significant outliers, and more importantly with an unacceptable low density for clinical applications. We propose a method to remove outliers and densify the maps of the state of the art for sparse endoscopy multi-map CudaSIFT-SLAM. The NN LightDepth for up-to-scale depth dense predictions are aligned with the sparse CudaSIFT submaps by means of the robust to spurious LMedS. Our system mitigates the inherent scale ambiguity in monocular depth estimation while filtering outliers, leading to reliable densified 3D maps. We provide experimental evidence of accurate densified maps 4.15 mm RMS accuracy at affordable computing time in the C3VD phantom colon dataset. We report qualitative results on the real colonoscopy from the Endomapper dataset. |
|
| Stitching the Story: Creating Panoramic Incident Summaries from Body-Worn Footage | 2025-09-04 | ShowFirst responders widely adopt body-worn cameras to document incident scenes and support post-event analysis. However, reviewing lengthy video footage is impractical in time-critical situations. Effective situational awareness demands a concise visual summary that can be quickly interpreted. This work presents a computer vision pipeline that transforms body-camera footage into informative panoramic images summarizing the incident scene. Our method leverages monocular Simultaneous Localization and Mapping (SLAM) to estimate camera trajectories and reconstruct the spatial layout of the environment. Key viewpoints are identified by clustering camera poses along the trajectory, and representative frames from each cluster are selected. These frames are fused into spatially coherent panoramic images using multi-frame stitching techniques. The resulting summaries enable rapid understanding of complex environments and facilitate efficient decision-making and incident review. |
5 pages, 3 figures |
| IL-SLAM: Intelligent Line-assisted SLAM Based on Feature Awareness for Dynamic Environments | 2025-09-03 | ShowVisual Simultaneous Localization and Mapping (SLAM) plays a crucial role in autonomous systems. Traditional SLAM methods, based on static environment assumptions, struggle to handle complex dynamic environments. Recent dynamic SLAM systems employ geometric constraints and deep learning to remove dynamic features, yet this creates a new challenge: insufficient remaining point features for subsequent SLAM processes. Existing solutions address this by continuously introducing addit |