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. SafeDriveVLA: Navigation-Conditioned World Model Dreaming for Conflict-Aware End-to-End Autonomous Driving

    Oct 14, 2026Shaoyuan Xie, Zihan Zhang, Jingxuan Wang +6Autonomous DrivingEnd-to-End Autonomous Driving

  2. ObjDream: Guiding Vision-Language-Action Models with Object-Level Understanding and Future State Prediction

    Oct 14, 2026Huailiang Ma, Yuxuan Li, Ziyi Zhao +7Vision-Language-Action ModelsRobustness of VLAs

  3. What Matters for World Modeling in Vision-Language-Action Models?

    Oct 14, 2026Qisen Ma, Yixiang Chen, Yuan Xu +10World Models for VLAsTemporal Modeling for VLAs

  4. End-to-End Vision-Language-Action Policies for Autonomous Lunar Rover Docking

    Oct 13, 2026Sitan Huang, Grace GaoSpace RoboticsVisuomotor Policy Learning

  5. VLA-GAUGE: Systematically Evaluating Generalization and Robustness in Vision-Language-Action Models

    Oct 12, 2026Jun Xiao, Rui Ye, Dong Cao +3OOD Generalization in VLAsRobustness of VLAs

  6. Same Goal, Different Words: Spatial Instruction Sensitivity in World-Action Models

    Oct 12, 2026Ali-Adeeb Abbas, Esmaeil Seraj, Behrad Toghi +1World Model EvaluationVision-Language-Action Models

  7. Barrier-Constrained Guidance For Real-time Asynchronous VLA Execution

    Oct 10, 2026Wenbo Yu, Jifan Li, Wenke Xia +5Inference-Time GuidanceEfficient VLA Inference

  8. Red-Teaming of Vision-Language-Action Models via Quality Diversity Environment Generation

    Oct 10, 2026Shihan Zhao, Henry Chen, Ya-Chuan Hsu +7Robustness of VLAsAdversarial Attacks on VLAs

  9. JitterVLA: A Replay Benchmark for Motion Quality in VLA-Driven Human-Robot Manipulation

    Oct 9, 2026Faith Ogunwoye, Didar Seyidov, Konstantin Gubernatorov +1Robotic ControlRobotic Policy Evaluation

  10. OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models

    Oct 9, 2026Xule Gao, Xi Wang, Zehua Zang +3Vision-Language-Action ModelsRobotic Manipulation

  11. VersaCamVLA: Camera-Configurable VLA Policies for Robotic Manipulation

    Oct 8, 2026Boyao Han, Chen Shi, Jingjing Qian +2Vision-Language-Action ModelsRobotic Manipulation

  12. CAPABLE: Capability-Aware Policy Adaptation via Behavioral Latent Encoding

    Oct 8, 2026Mohammad Khoshnazar, Mohammad Dehghani Tezerjani, Deyuan Qu +6Robot Policy AdaptationRobot Failure Recovery

  13. WARP-VLA: Wrist-Camera Adaptation for View-Robust Policy Execution in Vision-Language-Action Models

    Oct 8, 2026Junmyeong Lee, Dongmin Shin, Min-Gyu Park +3Robustness of VLAsVision-Language-Action Models

  14. When Listening Becomes Easier: Scrubbing Visual Cues for Shortcut-Free VLAs

    Oct 7, 2026Jasper Gerigk, Kenzo Aspuru-Takata, Chin-Hsuan Wu +3Vision-Language-Action ModelsRobustness of VLAs

  15. Do Vision-Language-Action Models Understand Instructions? A Mechanistic Interpretability Study on Language Grounding

    Oct 7, 2026Theodor Wulff, Angelo CangelosiVision-Language-Action ModelsRobustness of VLAs

  16. TMT: Runtime Backdoor Detection for Vision-Language-Action Policies on Unseen Tasks

    Oct 7, 2026Zirun Zhou, Jingfeng Zhang, HaoChuan Xu +4Backdoor Attacks on VLAsBackdoor Detection

  17. OGAM: Connecting Systematic Testing to Runtime Assurance through Object-Grounded Attention Monitoring for VLA Policies

    Oct 5, 2026Haki Darwish, Xiangyu Yin, Changwen Li +3Failure Detection for VLAsInstruction Generalization in VLAs

  18. Think Before You Distill: Generalization Recovery in Quantized VLAs via Selective Policy Distillation

    Oct 5, 2026Shen Ruan, Wenchang Gao, Jin Wang +4Vision-Language-Action ModelsOOD Generalization

  19. PerturBot: Breaking Shortcut Priors in Vision-Language-Action Models with Perturbative Training

    Oct 3, 2026Mingyu Liu, Chonghao Sima, Tianjian Feng +4Spatial Grounding for VLAsVision-Language-Action Models

  20. Detect and Suppress: A Mechanistic Defense against Adversarial Patches in VLA Models

    Oct 2, 2026Yukiya Horiba, Koshiro Aoki, Shunsuke Yasuki +2Robustness of VLAsAdversarial Patch Attacks

  21. MixVLA: Adaptive Mixing of Non-Invariant Information for Generalizable Vision-Language-Action Models

    Oct 2, 2026Pingrui Zhang, Yu Zhang, Pengyuan Wu +8OOD Generalization in VLAsVision-Language-Action Models

  22. World Action Modeling with Progressive Visual Planning

    Oct 1, 2026Fei Zhang, Zhaochong An, Duncan Frost +5World Model-Based PlanningRobot Task Planning

  23. Continuous Conditioning of VLAs with Augmenting EMG and Visual Task Descriptors

    Oct 1, 2026Edward W. Staley, Connor O. Pyles, Rahul Hingorani +5Robotic ControlVision-Language-Action Models