Robustness of VLA Models

VLA: Vision-Language-Action

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

221 papers57 papers in the last four weeks, up 78% on the four weeks before. 0.3% of all new papers.

Test-Time Training for Visual Foresight Vision-Language-Action Models
May 6, 2026Sangwu Park, Wonjoong Kim, Yeonjun In +3VLM Robustness Test-Time Training
KAIST, Seoul, South Korea.
Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms
Apr 26, 2026Qi Li, Bo Yin, Weiqi Huang +6AI Agent Safety Adversarial Attacks on VLA Models
National University of Singapore · Peking University · Monash University
How VLAs (Really) Work In Open-World Environments
Apr 23, 2026Amir Rasouli, Yangzheng Wu, Zhiyuan Li +4VLM Robustness Long-Horizon Robotic Manipulation
Noahs Ark Laboratory, Huawei Technologies Canada. · while at Huawei Canada.
Test-Time Perturbation Learning with Delayed Feedback for Vision-Language-Action Models
Apr 20, 2026Zehua Zang, Xi Wang, Fuchun Sun +4Test-Time Adaptation Test-Time Adaptation of VLMs
Institute of Software, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China · Tsinghua University, Beijing, China +2
STRONG-VLA: Decoupled Robustness Learning for Vision-Language-Action Models under Multimodal Perturbations
Apr 11, 2026Yuhan Xie, Yuping Yan, Yunqi Zhao +2Robustness of VLA Models Multimodal Robustness
Zhejiang University Hangzhou, China · Westlake University Hangzhou, China · Xidian University Xi’an, China
Uncovering Linguistic Fragility in Vision-Language-Action Models via Diversity-Aware Red Teaming
Apr 7, 2026Baoshun Tong, Haoran He, Ling Pan +2Adversarial Attacks on VLA Models Robustness of VLA Models
School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China · The Hong Kong University of Science and Technology, Hong Kong SAR, China
ICR-Drive: Instruction Counterfactual Robustness for End-to-End Language-Driven Autonomous Driving
Apr 7, 2026Kaiser Hamid, Can Cui, Nade LiangRobustness of VLA Models Autonomous Driving Safety Evaluation
Texas Tech University · Bosch Center for Artificial Intelligence (BCAI)
Open-Loop Planning, Closed-Loop Verification: Speculative Verification for VLA
Apr 3, 2026Zihua Wang, Zhitao Lin, Ruibo Li +4Closed-Loop Control of VLA Models Vision-Language-Action Models
School of Computer Science and Engineering, Southeast University, Nanjing, China · Nanyang Technological University, Singapore · School of Cyber Science and Engineering, Southeast University, Nanjing, China +1
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 VLA Models Adversarial Examples
East China Normal University · Zhongguancun Academy · CFAR, A*STAR, Singapore +2
MobiGuide: Vocabulary-Guided Online Recovery for Mobile Manipulation
Apr 2, 2026Jia Syuen Lim, Zhizhen Zhang, Peter Bohm +3Mobile Manipulation Diffusion Policy
UQMM Lab, The University of Queensland, Brisbane, Australia · Robotics and Autonomous Systems Group, CSIRO, Brisbane, Australia
LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models
Mar 30, 2026Chanyoung Kim, Minwoo Kim, Minseok Kang +2Vision-Language Grounding Vision-Language-Action Models
School of Computer Science and Engineering, Soongsil University, Seoul, Korea · Department of Artificial Intelligence, Chung-Ang University, Seoul, Korea
SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models
Mar 26, 2026Xiyang Wu, Guangyao Shi, Qingzi Wang +3Adversarial Attacks on VLA Models Robustness of VLA Models
University of Maryland, College Park, MD, USA · University of Southern California, Los Angeles, CA, USA · University of Central Florida, Orlando, FL, USA
TAG: Target-Agnostic Guidance for Stable Object-Centric Inference in Vision-Language-Action Models
Mar 25, 2026Jiaying Zhou, Zhihao Zhan, Ruifeng Zhai +5Vision-Language-Action Models Robustness of VLA Models
Sun Yat-sen University · Guangdong Key Lab of Big Data Analysis & Processing · X-Era AI Lab
RoboHarness: A Memory-Augmented Policy Harness for Vision-Language-Action Model Robustness via In-Context Adaptation
Mar 25, 2026Zhuoran Li, Zhiyang Li, Kaijun Zhou +1Robustness of VLA Models Test-Time Adaptation of VLA Models
School of Computer Science, Shanghai Jiao Tong University, Shanghai, China. · Shanghai Syslong Information Technology Co., Ltd.
TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches
Mar 24, 2026Zhengxian Huang, Wenjun Zhu, Haoxuan Qiu +2Adversarial Attacks on VLA Models Robustness of VLA Models
Zhejiang University, Hangzhou, China · Harbin Institute of Technology, Harbin, China
CoMaTrack: Competitive Multi-Agent Game-Theoretic Tracking with Vision-Language-Action Models
Mar 24, 2026Youzhi Liu, Li Gao, Liu Liu +2Game-Theoretic RL Reinforcement Learning
Amap, Alibaba Group
Do World Action Models Generalize Better than VLAs? A Robustness Study
Mar 23, 2026Zhanguang Zhang, Zhiyuan Li, Behnam Rahmati +11World Action Models Robustness of VLA Models
Huawei Technologies · University of Toronto
VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models
Mar 23, 2026Zixuan Wang, Yuxin Chen, Yuqi Liu +6Vision-Language-Action Models Reasoning for VLA Models
HKUST · CUHK · SmartMore
StageCraft: Execution Aware Mitigation of Distractor and Obstruction Failures in VLA Models
Mar 21, 2026Kartikay Milind Pangaonkar, Prabin Rath, Omkar Patil +1VLM Robustness Robotic Manipulation
Arizona State University
Red-Teaming Vision-Language-Action Models via Quality Diversity Prompt Generation for Robust Robot Policies
Mar 12, 2026Siddharth Srikanth, Freddie Liang, Ya-Chuan Hsu +9Robustness of VLA Models Adversarial Attacks on VLA Models
Thomas Lord Department of Computer Science, University of Southern California · Sony AI · Sibley School of Mechanical and Aerospace Engineering, Cornell University.
RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks
Mar 12, 2026Ruiying Li, Yunlang Zhou, YuYao Zhu +15Long-Horizon Robotic Manipulation VLMs for Robotics
AgiBot, China · National University of Singapore · Shanghai Jiao Tong University, Shanghai 200240, China +1
RC-NF: Robot-Conditioned Normalizing Flow for Real-Time Anomaly Detection in Robotic Manipulation
Mar 11, 2026Shijie Zhou, Bin Zhu, Jiarui Yang +3Robotic Anomaly Detection Anomaly Detection
Institute of Trustworthy Embodied AI, Fudan University · Shanghai Key Laboratory of Multimodal Embodied AI · Singapore Management University
Overcoming Visual Clutter in Vision Language Action Models via Concept-Gated Visual Distillation
Mar 11, 2026Sangmim Song, Sarath Kodagoda, Marc Carmichael +1Vision-Language-Action Models Robustness of VLA Models
University of Technology Sydney, NSW, Australia · Western Sydney University, NSW, Australia
See, Plan, Rewind: Progress-Aware Vision-Language-Action Models for Robust Robotic Manipulation
Mar 10, 2026Tingjun Dai, Mingfei Han, Tingwen Du +6Vision-Language-Action Models Language-Conditioned Robot Manipulation
School of Information Science and Technology, University of Science and Technology of China, Anhui, China. · University of Technology Sydney, Ultimo, NSW, Australia. · Department of Computer Vision, Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates. +3
AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models
Mar 9, 2026Xiaoquan Sun, Zetian Xu, Chen Cao +9Vision-Language-Action Models Robotic Manipulation
INFIFORCE Intelligent Technology Co., Ltd. Hangzhou, China · Huazhong University of Science and Technology, Wuhan, China · The University of Hong Kong, Hong Kong SAR, China +1
HSC-VLA: Hierarchical Scene-Clearing for Robust Bimanual Manipulation in Dense Clutter
Mar 8, 2026Zhen Liu, Xinyu Ning, Zhe Hu +3Robotic Manipulation Bimanual Robotic Manipulation
Beijing University of Posts and Telecommunications · InspireOmni AI · Tsinghua University
Restoring Linguistic Grounding in VLA Models via Train-Free Attention Recalibration
Mar 6, 2026Ninghao Zhang, Bin Zhu, Shijie Zhou +1Vision-Language-Action Models Robustness of VLA Models
Tsinghua University · Singapore Management University · Institute of Trustworthy Embodied AI, Fudan University +1
AnyCamVLA: Zero-Shot Camera Adaptation for Viewpoint Robust Vision-Language-Action Models
Mar 6, 2026Hyeongjun Heo, Seungyeon Woo, Sang Min Kim +4Test-Time Adaptation of VLA Models Robustness of VLA Models
Department of Electrical and Computer Engineering, Seoul National University, Seoul 08826, South Korea · Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA
Critic in the Loop: A Tri-System VLA Framework for Robust Long-Horizon Manipulation
Mar 5, 2026Pengfei Yi, Yingjie Ma, Wenjiang Xu +4Long-Horizon Robotic Manipulation VLMs for Robotics
Institute of Automation, Chinese Academy of Sciences · the School of Artificial Intelligence, University of Chinese Academy of Sciences
ATA: Bridging Implicit Reasoning with Attention-Guided and Action-Guided Inference for Vision-Language Action Models
Mar 2, 2026Cheng Yang, Jianhao Jiao, Lingyi Huang +8Vision-Language-Action Models Reasoning for VLA Models
Rutgers University · University College London · Rice University +1

May 6, 2026J/K move · Enter open · S save

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

Sangwu Park, Wonjoong Kim, Yeonjun In, Sein Kim+2

KAIST, Seoul, South Korea.

VLM Robustness Test-Time Training Vision-Language-Action Models Test-Time Adaptation of VLA Models Robustness of VLA Models

Open paper AskPDF arXiv

Visual Foresight VLA (VF-VLA) has become a prominent architectural choice in the recent VLA due to its impressive performance. Nevertheless, the inherent design of VF-VLA makes it particularly vulnerable to out-of-distribution (OOD) shifts. Because the quality of action directly depends on the accuracy of the predicted future visual information, OOD conditions affect both stages at once. To address this vulnerability, we propose Test-Time Training Visual Foresight VLA (

T^3

VF), a test-time training approach motivated by the observation that the predicted future image and its subsequent observation form a natural supervision pair. To further address the practical challenges that arise from indiscriminate test-time updates, we introduce an adaptive update filtering mechanism. Empirically,

T^3

VF mitigates the OOD vulnerability of VF-VLA at a modest additional inference cost, without requiring any architectural modification or auxiliary modules.