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. Imagining Recovery: Inference-Time Counterfactual Realignment for Vision-Language-Action Models

    Aug 14, 2026Yanyan Zhang, Disheng Liu, Kai Ye +6Vision-Language-Action ModelsRobustness of VLAs

  2. Policy-Induced Hand Priors in Humanoid Dual-Arm Manipulation: Diagnosing and Mitigating Initial-Pose Dependence

    Aug 12, 2026Chaeyeon Jung, Juyoun ParkBimanual Robotic ManipulationRobotic Manipulation

  3. Trajectory Divergence Horizon Decision for Reliable Dual-Arm Surgical Subtask Manipulation

    Aug 10, 2026Mingwu Su, Guankun Wang, Jinsong Lin +8Robotic ControlBimanual Robotic Manipulation

  4. Cross-View Action Consistency for Camera-Robust Vision-Language-Action Policies

    Aug 7, 2026Bingqi Huang, Bingchuan Wei, Xuan Wang +2Multi-View ConsistencyVision-Based Robot Control

  5. CofactVLA: Deconfounding Vision-Language-Action Models via Counterfactual Intervention

    Aug 5, 2026Yan Zhang, Yinan Wu, Haoran Duan +1Robotic ManipulationVision-Language-Action Models

  6. SAFECAST: Robust Failure Detection for VLA Policies with Contrast-Set Training and Calibration

    Aug 4, 2026Harshitha Rajaprakash, Aditeya Prajapati, Rong Xue +2Failure Detection for VLAsVision-Language-Action Models

  7. Unified Visuomotor Targets: Supervising VLAs Beyond Physical Actions

    Aug 4, 2026Zhenyang Feng, Unnat JainLatent Action LearningVisuomotor Policy Learning

  8. Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention Hijacking

    Aug 4, 2026Jinquan Zhang, Dongfu Yin, Run Yang +3Fine-TuningLanguage-Conditioned Robot Manipulation

  9. Grounded Semantic Re-Binding for Robust Instruction Generalization in Vision-Language-Action Models

    Aug 3, 2026Zhaokai Yin, Zhipeng ZhangVision-Language GroundingVision-Language-Action Models

  10. Uncovering and Mitigating Positional Blind Spots in Vision-Language-Action Models

    Aug 3, 2026Dongdong An, Pengjie Zhao, Yihao Huang +5Vision-Language-Action ModelsVLMs for Robotics

  11. OC-VLA++: Monocular Geometry-Guided Cross-View Consistency for Viewpoint-Robust Robotic Manipulation

    Aug 2, 2026Tianyi Zhang, Ziyang Gong, Zhenjie Yang +2Multi-View ConsistencyGeneralization in Robotic Manipulation

  12. VLAGuard: A Framework for Evaluating and Mitigating Physical Attention Hijacking in Vision-Language-Action Robots within Wireless Sensor Networks

    Aug 2, 2026Dongfu Yin, Jinquan ZhangAdversarial Patch AttacksAdversarial Attacks on VLAs

  13. ActFovea: Runtime Safeguarding for VLA Policies via Spatiotemporal Visual-Action Consistency

    Jul 31, 2026Wenda Yu, Tianshi Wang, Fengling Li +3Robot SafetyRobotic Manipulation

  14. ST-WAM: Semantic-Temporal World Action Model for Robust Manipulation under Visual Distribution Shifts

    Jul 31, 2026Mingxin Wang, Bin Hu, Bin Qian +12World Models for RoboticsGeneralization in Robotic Manipulation

  15. RoboBRIDGE: A Modular Framework for Bridging Policies to Robust Real-World Robotic Agents

    Jul 30, 2026Sihyung Yoon, Minjong Yoo, Sanghyun Ahn +2Long-Horizon Robotic ManipulationRobotics

  16. RL2^2-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models

    Jul 29, 2026Derek Ming Siang Tan, Shailesh Shailesh, Srikrishna Iyer +4Vision-Language-Action ModelsTest-Time Adaptation of VLAs

  17. CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Model

    Jul 28, 2026Minhyeok Lee, Chiyoung Kim, Chanhoe Gu +5Reasoning for VLAsEfficient VLA Inference

  18. FutureRTC: Real-Time Robot Execution with Anticipatory-Conditioned Action Chunking

    Jul 27, 2026Hai Jiang, Yixian Zou, Binbin Liang +3Vision-Language-Action ModelsAction Chunking

  19. MulRobBench: A Decision-Level Benchmark for Safe and Security-Policy-Compliant Multimodal UAV Agents

    Jul 26, 2026Belal S. Alsinglawi, Weizheng Wang, Junyi Wu +3Aerial RoboticsAI Agent Security Benchmarks

  20. STeP: Signal Temporal Logic for Precise Specifications for Action Generation with Vision Language Models

    Jul 20, 2026Kasra Torshizi, Anukriti Singh, Sidharth Mathur +3Language-Conditioned Robot ControlVLMs for Robotics

  21. Reasoning as a Double-Edged Sword: Architecture and Cross-Stage Robustness in Vision-Language-Action Models

    Jul 20, 2026Tuan Duong Trinh, Naveed Akhtar, Basim AzamNeural Network RobustnessAdversarial Attacks on VLAs

  22. AC-VLA: Robust Out-of-Distribution Action Execution via Compositional Learning

    Jul 17, 2026Xiaojiang Peng, Kai Peng, Jie Lu +3Robot Skill LearningGeneralization in Robotic Manipulation

  23. CosFly-VLA: A Spatially Aware Vision-Language-Action Model for UAV Tracking

    Jul 16, 2026Ruilong Ren, Songsheng Cheng, Yunpeng Zhou +9Aerial RoboticsVisual Object Tracking

  24. Learning Robust Execution in Robotic Manipulation with Agentic Reinforcement Learning

    Jul 15, 2026Xiaopeng Zhang, Yueyang Weng, Qi Liu +2Agentic RLRobot Failure Recovery