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. Semantic Anchoring for Robotic Action Representations

    Jul 15, 2026Yuan Xu, Youheng Shi, Chengyang Li +2Action Representation LearningGeneralization in Robotic Manipulation

  2. Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment

    Jul 15, 2026Dwip Dalal, Shivansh Patel, Chahit Jain +8VLA TrainingVision-Language-Action Models

  3. ChunkFlow: Towards Continuity-Consistent Chunked Policy Learning

    Jul 14, 2026Zhao Yang, Yinan Shi, Mingyuan Yao +3Visuomotor Policy LearningVision-Language-Action Models

  4. TrustVLA: Mechanism-Guided Inference-Time Defense Against Vision-Language-Action Backdoors

    Jul 14, 2026Pinhan Fu, Xianda Guo, Xuetao Li +5Adversarial Attacks on VLAsVision-Language-Action Models

  5. Artificial Foveated Perception for Mitigating Shortcut Learning in Robotic Foundation Models

    Jul 12, 2026Xiatao Sun, Yuan Zhuang, Mateo Sanchez Lopez Negrete +9Robot Foundation ModelsVisual Grounding

  6. SUREFlow: State-space Uncertainty-aware REsidual Flow Matching for Robust Robot Manipulation

    Jul 11, 2026Md Tanvir Islam, Sai Navaneet Peddapalli, Sangmoon Lee +1Flow MatchingUncertainty Estimation for VLAs

  7. CLAP: Direct VLM-to-VLA Adaptation via Language-Action Grounding

    Jul 9, 2026Yuri Ishitoya, Jeremy Siburian, Masashi Hamaya +5Robotic ManipulationVLM Adaptation

  8. Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents

    Jul 9, 2026Yixian Zhang, Huanming Zhang, Feng Gao +14Long-Horizon Robotic ManipulationLanguage-Conditioned Robot Manipulation

  9. From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model

    Jul 6, 2026Wenhao Li, Xueying Jiang, Quanhao Qian +4Language-Conditioned Robot ManipulationHand-Eye Calibration

  10. !Imperio, smolVLA: The Implications of Data Poisoning on Open Source Robotics

    Jul 5, 2026Stefan Bühler, Mark SchuteraNeural Network RobustnessAdversarial Attacks on VLAs

  11. CoRE-VLA: Towards Scalable and Robust Vision-Language-Action Modeling via Conditional Routing of Experts

    Jul 4, 2026Haozhe Zhang, Sixian Li, Yifei Zhang +5Multimodal RobustnessLanguage-Conditioned Robot Manipulation

  12. DREAMSTEER: Latent World Models Can Steer VLA Policies During Deployment Without Any Finetuning

    Jul 3, 2026Hanchen Cui, Sergio Arnaud, Arjun Majumdar +5World Model-Based PlanningRobotic Manipulation

  13. Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs

    Jul 2, 2026Junhao Shi, Siyin Wang, Xiaopeng Yu +3Self-Supervised Pre-TrainingEfficient VLAs

  14. Bridge-WA: Learning Action-Relevant World Dynamics for Robotic Manipulation

    Jul 2, 2026Yongjie Bai, Mingtong Dai, Zhouxia Wang +5World Models for RoboticsLanguage-Conditioned Robot Manipulation

  15. Guided Action Flow: Value-Guided Sampling for Frozen Vision-Language-Action Policies

    Jul 2, 2026Liuhaichen Yang, Zhuang Jiang, Chenchao Sheng +8Robotic ManipulationVision-Language-Action Models

  16. UniTacVLA: Unified Tactile Understanding and Prediction in Vision Language Action Models

    Jun 30, 2026Xidong Zhang, Yichi Zhang, Jiaxin Shi +5Visual-to-Tactile PredictionContact-Rich Robotic Manipulation

  17. Direct Action-Head Injection of A Grounded 3D Point Unlocks Spatial and Task Generalization

    Jun 26, 2026Shiang-Feng Tsai, Jin-Cheng Jhang, Yen-Ling Tai +5Vision-Language-Action ModelsGeneralization in Robotic Manipulation

  18. ROAD-VLA: Robust Online Adaptation via Self-Distillation for Vision-Language-Action Models

    Jun 24, 2026Kejing Wang, Toan Nguyen, Minh Hoang Nguyen +2Robustness of VLAsRobot Policy Adaptation

  19. VLA-FAIL: Efficient Task Failure Detection for Finetuned Vision-Language-Action Models

    Jun 19, 2026Florian Seligmann, Emiliyan Gospodinov, Enes Ulas Dincer +1Failure Detection for VLAsMahalanobis Distance

  20. Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement

    Jun 17, 2026Kinam Kim, Namiko Saito, Heecheol Kim +3Reinforcement LearningZero-Shot Robotic Manipulation

  21. Test-Time Improvement of VLA Policies via Selected Diffusion Noise for Spurious-Robust Action Smoothing

    Jun 12, 2026Duc Minh Nguyen, Bao-Ngoc Dao, Tung M. Luu +15Diffusion PolicyRobotic Manipulation

  22. Trajectory-Level Redirection Attacks on Vision-Language-Action Models

    Jun 11, 2026Gokul Puthumanaillam, Vardhan Dongre, Pranay Thangeda +3Language-Conditioned Robot ManipulationAdversarial Attacks on VLAs