Robustness of VLAs

VLA: Vision-Language-Action Model

Overview

This field studies whether robots guided by vision-language-action models can follow instructions and act reliably when viewpoints, lighting, objects, sensor inputs, or robot execution differ from training. Training approaches include perturbation and counterfactual data, consistency objectives, and world-model supervision; inference-time methods use adaptation, monitoring, action correction, and failure recovery. Benchmarks such as LIBERO-Plus and RoboTwin test shifts in simulation, while real-robot evaluations expose hardware faults and contact-related failures; increasingly, evaluations measure safety and behavior over a rollout, not just task completion. A central challenge is improving performance under distribution shift without weakening clean-task performance, sensitivity to meaningful instructions, or safe behavior.

Latest papers

CardsList

239 papers20 papers in the last four weeks, down 67% on the four weeks before. 0.2% of all new papers.

  1. Uncovering Vulnerability of Vision-Language-Action Models under Joint-Level Physical Faults

    Jun 9, 2026Minsoo Jo, Taeju Kwon, Junha Chun +2Robotic ControlVision-Language-Action Models

  2. ProbeAct: Probe-Guided Training-Free Failure Recovery in Vision-Language-Action Models

    Jun 8, 2026Fan Zhang, Seongbin Park, Baharan Mirzasoleiman +2VLM RobustnessRobot Failure Recovery

  3. ReCoVLA: VLM-Guided Reward Compilation for Failure Recovery in Vision-Language-Action Policies

    Jun 8, 2026Haodi Hu, Chung-Ta Huang, Jing Liu +4Robot Failure RecoveryVision-Language-Action Models

  4. Scaling by Diversified Experience for Vision-Language-Action Models

    Jun 8, 2026Leiyu Wang, Zhaofengnian Wang, Xueqi Li +3VLM RobustnessVision-Language-Action Models

  5. Benchmarking Vision-Language-Action Models on SO-101: Failure and Recovery Analysis

    Jun 7, 2026Yi Yu, Xinchuan QiuRobot Policy LearningRobotic Manipulation

  6. FATE-VLA:Failue-aware test generation for vision-language-action models

    Jun 1, 2026Arusa Kanwal, Pablo Valle, Shaukat Ali +1VLM EvaluationVision-Language-Action Models

  7. Make Your VLA More Robust Without More Data By Interleaving Motion Planning

    May 31, 2026Dan BW Choe, Sundhar Vinodh Sangeetha, Samuel Coogan +1VLM RobustnessLong-Horizon Robotic Manipulation

  8. ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving

    May 27, 2026Mohammadreza Teymoorianfard, Jean-Philippe Monteuuis, Jonathan Petit +1VLMs for Autonomous DrivingAutonomous Driving Safety Evaluation

  9. From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model

    May 21, 2026Bing Hu, Zaijing Li, Rui Shao +4Visuomotor Policy LearningRobotic Manipulation

  10. Lost in Fog: Sensor Perturbations Expose Reasoning Fragility in Driving VLAs

    May 20, 2026Abhinaw Priyadershi, Jelena FrtunikjVLM RobustnessVLMs for Autonomous Driving

  11. RoVLA: Multi-Consistency Constraints for Robust Vision-Language-Action Models

    May 19, 2026Jingzhou Luo, Yifan Wen, Yongjie Bai +3VLM RobustnessLanguage-Conditioned Robot Manipulation

  12. StableVLA: Towards Robust Vision-Language-Action Models without Extra Data

    May 18, 2026Yiyang Fu, Chubin Zhang, Shukai Gong +7Image Corruption RobustnessVision-Language-Action Models

  13. Is VLA Reasoning Faithful? Probing Safety of Chain-of-Causation in Autonomous Driving Models

    May 17, 2026Nicanor Mayumu, Xiaoheng Deng, Patrick MukalaCoT FaithfulnessVLMs for Autonomous Driving

  14. VLAMotor: Test-Guided Enhancement of Vision-Language-Action Models via Agent-BasedData Synthesis

    May 16, 2026Zeqin Liao, Peifan Ren, Zixu Gao +6VLM AdaptationSynthetic Data Generation for Robotics

  15. RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models

    May 10, 2026Weijia Liufu, Xiaoyu Guo, Ruiyi Chen +16VLM RobustnessRobot Failure Recovery

  16. Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Models

    May 8, 2026Meng Zheng, Samhita Marri, Anwesa Choudhuri +6Diffusion PolicyRobotic Manipulation

  17. Test-Time Training for Visual Foresight Vision-Language-Action Models

    May 6, 2026Sangwu Park, Wonjoong Kim, Yeonjun In +3VLM RobustnessTest-Time Training

  18. Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms

    Apr 26, 2026Qi Li, Bo Yin, Weiqi Huang +6AI Agent SafetyAdversarial Attacks on VLAs

  19. How VLAs (Really) Work In Open-World Environments

    Apr 23, 2026Amir Rasouli, Yangzheng Wu, Zhiyuan Li +4VLM RobustnessLong-Horizon Robotic Manipulation

  20. Test-Time Perturbation Learning with Delayed Feedback for Vision-Language-Action Models

    Apr 20, 2026Zehua Zang, Xi Wang, Fuchun Sun +4Test-Time AdaptationTest-Time Adaptation of VLMs

  21. STRONG-VLA: Decoupled Robustness Learning for Vision-Language-Action Models under Multimodal Perturbations

    Apr 11, 2026Yuhan Xie, Yuping Yan, Yunqi Zhao +2Robustness of VLAsMultimodal Robustness

  22. Uncovering Linguistic Fragility in Vision-Language-Action Models via Diversity-Aware Red Teaming

    Apr 7, 2026Baoshun Tong, Haoran He, Ling Pan +2Adversarial Attacks on VLAsRobustness of VLAs

  23. ICR-Drive: Instruction Counterfactual Robustness for End-to-End Language-Driven Autonomous Driving

    Apr 7, 2026Kaiser Hamid, Can Cui, Nade LiangRobustness of VLAsAutonomous Driving Safety Evaluation

  24. Open-Loop Planning, Closed-Loop Verification: Speculative Verification for VLA

    Apr 3, 2026Zihua Wang, Zhitao Lin, Ruibo Li +4Closed-Loop Control of VLAsVision-Language-Action Models

  25. Tex3D: Objects as Attack Surfaces via Adversarial 3D Textures for Vision-Language-Action Models

    Apr 2, 2026Jiawei Chen, Simin Huang, Jiawei Du +5Adversarial Attacks on VLAsAdversarial Examples

  26. MobiGuide: Vocabulary-Guided Online Recovery for Mobile Manipulation

    Apr 2, 2026Jia Syuen Lim, Zhizhen Zhang, Peter Bohm +3Mobile ManipulationDiffusion Policy

  27. LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models

    Mar 30, 2026Chanyoung Kim, Minwoo Kim, Minseok Kang +2Vision-Language GroundingVision-Language-Action Models

  28. SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models

    Mar 26, 2026Xiyang Wu, Guangyao Shi, Qingzi Wang +3Adversarial Attacks on VLAsRobustness of VLAs