{"total":18,"rows":[{"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":"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":"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":"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":"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":"2606.27079","title":"ForesightSafety-VLA: A Unified Diagnostic Safety Benchmark for Vision-Language-Action Models","created":"2026-06-25","cited_by_count":3,"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":"2606.13886","title":"PhysVLA: Towards Physically-Grounded VLA for Embodied Robotic Manipulation","created":"2026-06-11","cited_by_count":1,"area":"vla"},{"id":"2608.00315","title":"Towards General Language-Conditioned Latent Safety Filters","created":"2026-07-31","cited_by_count":1,"area":"vla"},{"id":"2601.21712","title":"CoFreeVLA: Short-Horizon Collision-Free Dual-Arm Manipulation via Vision-Language-Action Model and Risk Estimation","created":"2026-01-29","cited_by_count":0,"area":"vla"},{"id":"2606.00515","title":"PaCo-VLA: Passivity-Shielded Compliance Prior for Contact-Rich Vision-Language-Action Manipulation","created":"2026-05-30","cited_by_count":0,"area":"vla"},{"id":"2606.09740","title":"ProbeAct: Probe-Guided Training-Free Failure Recovery in Vision-Language-Action Models","created":"2026-06-08","cited_by_count":0,"area":"vla"},{"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":"2609.28984","title":"CrossSafe: Towards Cross-Embodiment Latent Safety Filters","created":"2026-09-24","cited_by_count":0,"area":"vla"},{"id":"2609.33256","title":"ActionGround: Training-Free Runtime Refinement of Frozen VLA Policies","created":"2026-09-27","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":"2609.40007","title":"Multi-Link Safety Filtering for VLA Policies Around Moving Hazards","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"}],"next_cursor":null}