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. Is Success All You Need? Investigating the Impact of Input Perturbations on VLA Behaviour in Tabletop Manipulation Tasks

    Oct 1, 2026Sophie Higham, Riccardo Andrea Izzo, Matteo Matteucci +1Vision-Language-Action ModelsRobot Manipulation Benchmarks

  2. Multi-Link Safety Filtering for VLA Policies Around Moving Hazards

    Sep 30, 2026Yatharth Agarwal, Vijay RaghunathanRobot SafetySafety Filtering

  3. When Instructions Retrieve Trajectories: Diagnosing and Mitigating Generalization Failures in VLA Models

    Sep 30, 2026Hung-Jen Chen, Yu-Hsun Hou, Yan-Hong Chen +4Robotic ManipulationVision-Language-Action Models

  4. Blackout vs. Freeze: Analyzing Physical Failure Modes of VLAs under Camera Faults

    Sep 30, 2026Heejae Suh, Jongwook Han, Zahra Gholami +1Robotic ControlVision-Language-Action Models

  5. Beyond Prediction: Steering VLM Agents with Retrospective World Modeling

    Sep 30, 2026Yongjiang Liu, Jie Zhang, Haoyue Zhang +3World Model LearningWorld Models

  6. Refusals That Bend: Measuring and Predicting Task Malleability in Embodied VLM Planners

    Sep 30, 2026Leo Y. Lin, Mikhail Kuznetsov, Muslum Ozgur Ozmen +1Robot SafetyLLM Safety Evaluation

  7. RawVLA: Embodied Neural Image Signal Processor For Robotic Manipulation

    Sep 29, 2026Shuhong Liu, Heng Zhou, Lingfeng Qian +7Robotic ManipulationVision-Language-Action Models

  8. Disentangling Spurious Correlations in Vision-Language-Action Models via Predicting Domain-Invariant Latent Lookahead

    Sep 29, 2026Junghyun Kim, Ngseo Kim, ChungWoo Lee +7Domain GeneralizationVision-Language-Action Models

  9. CoRe-VLA: Preserving Cross-View Coordination in VLAs under Camera Shifts

    Sep 29, 2026Tianhang Pan, Xuanhao Wang, Yiwen Pang +4Point Cloud Surface ReconstructionVision-Language-Action Models

  10. Where Predictive Supervision Goes Shapes What VLA Policies Learn

    Sep 29, 2026Hanseul Kim, Jewon Yeom, Youngjoon Jeong +2Visuomotor Policy LearningVision-Language-Action Models

  11. Learning to Act under Visual Interruptions with Vision-Language-Action Models

    Sep 28, 2026Mingle Jiang, Rui Xu, Yunke Wang +1Vision-Language-Action ModelsVision-Based Robot Control

  12. ActionUNet: Improving Robustness of VLA Models with Efficient Multi-scale Fine-tuning

    Sep 28, 2026Di Zhu, Ziheng Yan, Fang WanRobotic ControlEfficient VLAs

  13. RoboIRGBench: Benchmarking Implicit Referential Grounding in Vision-Language-Action Models

    Sep 28, 2026Aernaer Akelijiang, Jiannan Li, Zhineng Chen +2Language-Conditioned Robot ManipulationVision-Language-Action Models

  14. TLC-DiT: Task-Aligned Local Visual Conditioning for Robust Multitask Robot Manipulation

    Sep 28, 2026Xianbo Cai, Hideyuki Ichiwara, Zihang Wang +2Language-Conditioned Robot ManipulationMulti-Task Robotic Manipulation

  15. Does Adversarial Training Improve Generalization in Multi-View VLAs? Revealing and Mitigating View Collapse

    Sep 27, 2026Futa Waseda, Shuhei Kurita, Isao EchizenAdversarial TrainingMulti-View Learning

  16. ActionGround: Training-Free Runtime Refinement of Frozen VLA Policies

    Sep 27, 2026Namai Chandra, Madhur Thareja, Shriram Damodaran +1Robotic ControlVision-Language-Action Models

  17. DS-VLA: A Dendritic-inspired Vision-Language-Action Model for Robust Action Control

    Sep 26, 2026Yaxing Lyu, Jingyi Li, Mingkun Xu +1Vision-Language-Action ModelsRobustness of VLAs

  18. FRAM: Trajectory-Guided Visual Feature Selection for Compact Language-Conditioned Robot Manipulation

    Sep 25, 2026Hiroshi Ito, Hyogo Hiruma, Yoshiki Kanai +3Language-Conditioned Robot ManipulationEfficient VLAs

  19. Self-Adaptive VLA for Robust Robot Deployment

    Sep 24, 2026Hongxin Zhang, Chunru Lin, Tsun-Hsuan Wang +2Robot Policy LearningRobot Policy Adaptation

  20. InfiNoVA: Infinite Novel View Augmentation for Viewpoint Invariant Robot Policies

    Sep 23, 2026Sai Puneeth Reddy Gottam, Elmar Rueckert, Vedant DaveRobot LearningRobustness of VLAs

  21. IndustrialVLA-Bench: A Traceable Multi-Axis Evaluation of Open Robot Policy Models

    Sep 22, 2026Yiqi Wang, Zhifeng Rao, Jiaqi Zhang +7Robotic Policy EvaluationVision-Language-Action Models

  22. LIBERO-VPro: Benchmarking Closed-Loop Visual Robustness of Robotic Foundation Models

    Sep 21, 2026Huiqiong Li, Zhiting Mei, Anirudha Majumdar +3World Models for RoboticsRobot Foundation Models

  23. CARE: Experience-Guided Atomic Corrective Execution for Vision-Language-Action Policies

    Sep 21, 2026Junlan Xiao, Junwei Jiang, Zaibin Zhang +4Long-Horizon Robotic ManipulationVision-Language-Action Models

  24. Beyond Appearance Shifts: Task-Semantic Action Calibration for VLA Models

    Sep 20, 2026Shuaijun Liu, Feiyang You, Chengyu Wu +6Vision-Language-Action ModelsVLMs for Robotics

  25. MaskVLA: Visual Masking Against Trajectory Overfitting of Vision-Language-Action Model

    Sep 20, 2026Yuxuan Jiang, Jiaying Huang, Ge Wang +9Robotic ManipulationVision-Language-Action Models

  26. An Empirical Study and Open Testbed for Federated Fine-Tuning of Vision-Language-Action Models

    Sep 19, 2026Zhekai Duan, Kevin Ziyang Xie, Xinyu Tan +5Vision-Language-Action ModelsVLMs for Robotics