{"total":72,"rows":[{"id":"2507.01925","title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","created":"2025-07-02","cited_by_count":96,"area":"vla"},{"id":"2509.19012","title":"Pure Vision Language Action (VLA) Models: A Comprehensive Survey","created":"2025-09-23","cited_by_count":49,"area":"mllm"},{"id":"2512.11891","title":"VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer","created":"2025-12-09","cited_by_count":34,"area":"vla"},{"id":"2512.22539","title":"VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models","created":"2025-12-27","cited_by_count":31,"area":"vla"},{"id":"2503.17682","title":"Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback","created":"2025-03-22","cited_by_count":30,"area":"mllm"},{"id":"2511.18960","title":"AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention","created":"2025-11-24","cited_by_count":25,"area":"vla"},{"id":"2503.21819","title":"Optimizing Safe and Aligned Language Generation: A Multi-Objective GRPO Approach","created":"2025-03-26","cited_by_count":24,"area":"lr"},{"id":"2509.19870","title":"FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Models","created":"2025-09-24","cited_by_count":21,"area":"vla"},{"id":"2602.05073","title":"Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities","created":"2026-02-04","cited_by_count":20,"area":"agents"},{"id":"2605.03941","title":"iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework","created":"2026-05-05","cited_by_count":14,"area":"wm"},{"id":"2505.18531","title":"Generative RLHF-V: Learning Principles from Multi-modal Human Preference","created":"2025-05-24","cited_by_count":13,"area":"mllm"},{"id":"2509.22407","title":"EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfer","created":"2025-09-26","cited_by_count":12,"area":"vla"},{"id":"2603.06001","title":"Restoring Linguistic Grounding in VLA Models via Train-Free Attention Recalibration","created":"2026-03-06","cited_by_count":12,"area":"vla"},{"id":"2606.23686","title":"LIBERO-Safety: A Comprehensive Benchmark for Physical and Semantic Safety in Vision-Language-Action Models","created":"2026-06-22","cited_by_count":10,"area":"vla"},{"id":"2606.00773","title":"SafeVLA-Bench: A Benchmark for the Success-Safety Gap in Vision-Language-Action Models","created":"2026-05-30","cited_by_count":9,"area":"vla"},{"id":"2604.12447","title":"HazardArena: Evaluating Semantic Safety in Vision-Language-Action Models","created":"2026-04-14","cited_by_count":8,"area":"vla"},{"id":"2606.05468","title":"FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization","created":"2026-06-03","cited_by_count":8,"area":"vla"},{"id":"2509.15968","title":"CoReVLA: A Dual-Stage End-to-End Autonomous Driving Framework for Long-Tail Scenarios via Collect-and-Refine","created":"2025-09-19","cited_by_count":7,"area":"driving"},{"id":"2604.08476","title":"Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization","created":"2026-04-09","cited_by_count":6,"area":"lr"},{"id":"2606.12372","title":"UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning","created":"2026-06-10","cited_by_count":6,"area":"agents"},{"id":"2603.05754","title":"Safe-Night VLA: Seeing the Unseen via Thermal-Perceptive Vision-Language-Action Models for Safety-Critical Manipulation","created":"2026-03-05","cited_by_count":5,"area":"vla"},{"id":"2603.14367","title":"HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task","created":"2026-03-15","cited_by_count":5,"area":"mllm"},{"id":"2511.01472","title":"AERMANI-VLM: Structured Prompting and Reasoning for Aerial Manipulation with Vision Language Models","created":"2025-11-03","cited_by_count":4,"area":"lr"},{"id":"2605.07381","title":"Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation","created":"2026-05-08","cited_by_count":4,"area":"vla"},{"id":"2605.28083","title":"VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking","created":"2026-05-27","cited_by_count":4,"area":"vla"},{"id":"2606.09749","title":"Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models","created":"2026-06-08","cited_by_count":4,"area":"vla"},{"id":"2606.12299","title":"Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering","created":"2026-06-10","cited_by_count":4,"area":"vla"},{"id":"2607.01378","title":"Neuro-Symbolic Safety Guidance for Vision-Language-Action Models via Constrained Flow Matching","created":"2026-07-01","cited_by_count":4,"area":"vla"},{"id":"2603.11987","title":"LABSHIELD: A Multimodal Benchmark for Safety-Critical Reasoning and Planning in Scientific Laboratories","created":"2026-03-12","cited_by_count":3,"area":"lr"},{"id":"2606.12403","title":"World Pilot: Steering Vision-Language-Action Models with World-Action Priors","created":"2026-06-10","cited_by_count":3,"area":"wm"},{"id":"2609.20822","title":"Coding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation","created":"2026-09-17","cited_by_count":3,"area":"agents"},{"id":"2602.05863","title":"Constrained Group Relative Policy Optimization","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2604.12656","title":"FeaXDrive: Feasibility-aware Trajectory-Centric Diffusion Planning for End-to-End Autonomous Driving","created":"2026-04-14","cited_by_count":2,"area":"driving"},{"id":"2605.04539","title":"RLearner-LLM: Balancing Logical Grounding and Fluency in Large Language Models via Hybrid Direct Preference Optimization","created":"2026-05-06","cited_by_count":2,"area":"alignment"},{"id":"2605.09005","title":"Towards Backdoor-Based Ownership Verification for Vision-Language-Action Models","created":"2026-05-09","cited_by_count":2,"area":"vla"},{"id":"2606.20698","title":"SafeDojo: Safe Reinforcement Learning for VLA via Interactive World Model","created":"2026-06-15","cited_by_count":2,"area":"wm"},{"id":"2606.22278","title":"X-Safe: Embodiment-Agnostic Safeguarding for Robot Arm Manipulation Policies via Action Masking","created":"2026-06-21","cited_by_count":2,"area":null},{"id":"2606.31045","title":"LabGuard: Grounding Natural-Language Laboratory Rules into Runtime Guards for Embodied Laboratory Agents","created":"2026-06-30","cited_by_count":2,"area":null},{"id":"2607.04234","title":"SoftVTBench: A Safety-Aware Visuo-Tactile Benchmark for Physically Constrained Robotic Manipulation of Deformable Objects (Early Version)","created":"2026-07-05","cited_by_count":2,"area":null},{"id":"2607.28226","title":"Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and Evaluation","created":"2026-07-30","cited_by_count":2,"area":"wm"},{"id":"2607.29169","title":"ActFovea: Runtime Safeguarding for VLA Policies via Spatiotemporal Visual-Action Consistency","created":"2026-07-31","cited_by_count":2,"area":"vla"},{"id":"2607.29569","title":"Safe Vision Language Action Models via Barrier Enhanced Flow Matching","created":"2026-07-31","cited_by_count":2,"area":"vla"},{"id":"2603.11975","title":"HomeSafe-Bench: Evaluating Vision-Language Models on Unsafe Action Detection for Embodied Agents in Household Scenarios","created":"2026-03-12","cited_by_count":1,"area":"mllm"},{"id":"2604.22591","title":"RedVLA: Physical Red Teaming for Vision-Language-Action Models","created":"2026-04-24","cited_by_count":1,"area":"vla"},{"id":"2608.01573","title":"Uncovering and Mitigating Positional Blind Spots in Vision-Language-Action Models","created":"2026-08-03","cited_by_count":1,"area":"vla"},{"id":"2608.21740","title":"CounterAlign: Counterfactual Supervision for Vision-Language-Action Models","created":"2026-08-22","cited_by_count":1,"area":"vla"},{"id":"2609.34041","title":"Vision--Language Signals in Constrained RL: Safety Gains Without Anticipation","created":"2026-09-28","cited_by_count":1,"area":"deeprl"},{"id":"2603.09706","title":"OOD-MMSafe: Advancing MLLM Safety from Harmful Intent to Hidden Consequences","created":"2026-03-10","cited_by_count":0,"area":"mllm"},{"id":"2603.17969","title":"Specification-Aware Distribution Shaping for Robotics Foundation Models","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2605.28726","title":"How VLAs Fail Differently: Black-Box Action Monitoring Reveals Architecture-Specific Failure Signatures","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.03954","title":"VLESA: Vision-Language Embodied Safety Agent for Human Activity Monitoring","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.08414","title":"PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulation","created":"2026-06-07","cited_by_count":0,"area":"diffusion"},{"id":"2606.11266","title":"Seeing Before Colliding: Anticipatory Safe RL with Frozen Vision-Language Models","created":"2026-06-09","cited_by_count":0,"area":"mllm"},{"id":"2607.03283","title":"Embodied Operators and Benchmarking: Toward Reusable and Deployable Embodied Intelligence Systems","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2607.07403","title":"Multi-Agent Robotic Control with Onboard Vision-Language Models","created":"2026-07-08","cited_by_count":0,"area":"agents"},{"id":"2607.12571","title":"TrustVLA: Mechanism-Guided Inference-Time Defense Against Vision-Language-Action Backdoors","created":"2026-07-14","cited_by_count":0,"area":"vla"},{"id":"2608.16843","title":"Security of Foundation-Model-Powered Embodied Agents: Attack Surfaces, Attacks, Defenses, and Evaluation","created":"2026-08-17","cited_by_count":0,"area":"agents"},{"id":"2608.19729","title":"SafeBranch: Branch-Pair Safety Alignment for Embodied Agents","created":"2026-08-20","cited_by_count":0,"area":"alignment"},{"id":"2608.20556","title":"Logic-VLA: A Temporal Logic Conditioned Vision-Language-Action Model","created":"2026-08-20","cited_by_count":0,"area":"vla"},{"id":"2609.04277","title":"FailureSpot: Label-Efficient Timestamp-Level Failure Detection for Vision-Language-Action Models","created":"2026-09-03","cited_by_count":0,"area":"vla"},{"id":"2609.08444","title":"Safe Task Planning with Long-Term Graph Memory for Embodied Agents","created":"2026-09-08","cited_by_count":0,"area":"mllm"},{"id":"2609.13231","title":"ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models","created":"2026-09-02","cited_by_count":0,"area":"vla"},{"id":"2609.22285","title":"ORDER: A Fictitious-World Benchmark for Domain-Adaptive Embodied AI","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.22462","title":"VLPSA: Vision-Language-Poisson-Safe Actions for Full-Body Safety of Learned Policies","created":"2026-09-18","cited_by_count":0,"area":"vla"},{"id":"2609.27847","title":"Security and Privacy in Large-Model-Driven Embodied Agents: Attacks, Defenses, and Future Directions","created":"2026-08-19","cited_by_count":0,"area":"agents"},{"id":"2609.30709","title":"VLALight: Lightweight Vision-Language-Action Models for Emergency-Aware Traffic Signal Control","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.31792","title":"ConflictVLA-Bench: Benchmarking Behavioral Responses of Vision-Language-Action Models to Premise Conflicts","created":"2026-09-25","cited_by_count":0,"area":"vla"},{"id":"2609.39820","title":"Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models","created":"2026-09-30","cited_by_count":0,"area":"vla"},{"id":"2610.01083","title":"WBAG: A Whole-Body and Attached-Geometry Safety Framework for Vision-Language-Action Manipulation","created":"2026-10-01","cited_by_count":0,"area":"vla"},{"id":"2610.05025","title":"Triggering Generalist Reasoning via Predictive Uncertainty for Dual-System VLA","created":"2026-10-04","cited_by_count":0,"area":"vla"},{"id":"2610.05166","title":"A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies","created":"2026-10-04","cited_by_count":0,"area":"vla"},{"id":"2610.05878","title":"OGAM: Connecting Systematic Testing to Runtime Assurance through Object-Grounded Attention Monitoring for VLA Policies","created":"2026-10-05","cited_by_count":0,"area":"vla"}],"next_cursor":null}