Robustness of VLA Models

VLA: Vision-Language-Action

Follow this topic Ask about this topic

Momentum

35 papers in the last four weeks, up 338% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 142

All topics

VersaCamVLA: Camera-Configurable VLA Policies for Robotic Manipulation
Oct 8, 2026Boyao Han, Chen Shi, Jingjing Qian +2Vision-Language-Action Models Robotic Manipulation
The Chinese University of Hong Kong, Shenzhen · Shenzhen Loop Area Institute · Harbin Institute of Technology, Shenzhen
CAPABLE: Capability-Aware Policy Adaptation via Behavioral Latent Encoding
Oct 8, 2026Mohammad Khoshnazar, Mohammad Dehghani Tezerjani, Deyuan Qu +6Robot Policy Adaptation Robot Failure Recovery
University of Bremen, Bremen, Germany. · University of North Texas, Denton, TX, USA. · Toyota Motor North America, InfoTech Labs, Mountain View, CA, USA.
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 VLA Models Vision-Language-Action Models
Yonsei University. · Korea Electronics Technology Institute(KETI).
When Listening Becomes Easier: Scrubbing Visual Cues for Shortcut-Free VLAs
Oct 7, 2026Jasper Gerigk, Kenzo Aspuru-Takata, Chin-Hsuan Wu +3Vision-Language-Action Models Robustness of VLA Models
University of Toronto, Toronto, ON M5S 3H5, Canada · Vector Institute, Toronto, ON M5G 0C6, Canada
Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action Models
Oct 7, 2026Mikey Watts, Yuchen CuiRobustness of VLA Models Instruction Generalization in VLA Models
Independent Researcher · University of California, Los Angeles
Do Vision-Language-Action Models Understand Instructions? A Mechanistic Interpretability Study on Language Grounding
Oct 7, 2026Theodor Wulff, Angelo CangelosiVision-Language-Action Models Robustness of VLA Models
Department of Computer Science The University of Manchester Manchester, United Kingdom
TMT: Runtime Backdoor Detection for Vision-Language-Action Policies on Unseen Tasks
Oct 7, 2026Zirun Zhou, Jingfeng Zhang, HaoChuan Xu +4Backdoor Detection Robustness of VLA Models
The University of Auckland · Fudan University · Institute of Science Tokyo
DIVA: Dual-Space Intent-Aware Visual Attenuation for Vision-Language-Action Policies
Oct 6, 2026Kaixi Feng, Guoheng Sun, Ziyao Wang +3Vision-Language-Action Models Robustness of VLA Models
University of Maryland, College Park
Adapting Vision-Language-Action Models to Unknown Visual Disruptions During Execution
Oct 6, 2026Ahin Lee, Jinwoo Seo, Youngsoo Jang +1Robot Policy Adaptation Test-Time Adaptation of VLA Models
UNIST, Ulsan, Republic of Korea
How (and How Not) to Use Data Augmentation in VLA Post-Training
Oct 5, 2026Bram Grooten, Joaquin VanschorenRL Post-Training Robustness of VLA Models
TU Eindhoven
OGAM: Connecting Systematic Testing to Runtime Assurance through Object-Grounded Attention Monitoring for VLA Policies
Oct 5, 2026Haki Darwish, Xiangyu Yin, Changwen Li +3Instruction Generalization in VLA Models Robustness of VLA Models
Carl von Ossietzky University of Oldenburg, Germany · Huadian Electric Power Research Institute, China · Institute of Software, Chinese Academy of Science, China +1
Beyond In-Distribution Preservation: Recovering Generalization in Quantized VLAs via Vulnerability-Oriented Tuning
Oct 5, 2026Shen Ruan, Wenchang Gao, Jin Wang +4VLM Quantization OOD Generalization
Soochow University · Independent Researcher · Shanghai Jiao Tong University +2
Continuous Conditioning of VLAs with Augmenting EMG and Visual Task Descriptors
Oct 1, 2026Edward W. Staley, Connor O. Pyles, Rahul Hingorani +5Robotic Control Vision-Language-Action Models
Johns Hopkins Applied Physics Laboratory Laurel, MD, USA
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 Models Robot Manipulation Benchmarks
School of Informatics, University of Edinburgh, UK · Department of Electronics, Informatics and Bioengineering, Politecnico di Milano, Italy
Multi-Link Safety Filtering for VLA Policies Around Moving Hazards
Sep 30, 2026Yatharth Agarwal, Vijay RaghunathanRobot Safety Safety Filtering
School of Electrical and Computer Engineering Purdue University, West Lafayette, IN, USA
EWAM: Emergent Depth-Wise Specialization in a Unified Embodied Model -- From Semantic Understanding through Visual Foresight to Action
Sep 30, 2026Hao Wang, Jiajun Wen, Jingzhi Liu +21Vision-Language-Action Models Robustness of VLA Models
Yinwang Intelligent Technology Co. Ltd.
When Instructions Retrieve Trajectories: Diagnosing and Mitigating Generalization Failures in VLA Models
Sep 30, 2026Hung-Jen Chen, Yu-Hsun Hou, Yan-Hong Chen +4Robotic Manipulation Vision-Language-Action Models
National Tsing Hua University · National Taiwan University
Blackout vs. Freeze: Analyzing Physical Failure Modes of VLAs under Camera Faults
Sep 30, 2026Heejae Suh, Jongwook Han, Zahra Gholami +1Robotic Control Vision-Language-Action Models
Seoul National University, Seoul, Republic of Korea
Beyond Prediction: Steering VLM Agents with Retrospective World Modeling
Sep 30, 2026Yongjiang Liu, Jie Zhang, Haoyue Zhang +3World Model Learning World Models
The Hong Kong University of Science and Technology · The Hong Kong Polytechnic University · China University of Geoscience
Refusals That Bend: Measuring and Predicting Task Malleability in Embodied VLM Planners
Sep 30, 2026Leo Y. Lin, Mikhail Kuznetsov, Muslum Ozgur Ozmen +1Robot Safety LLM Safety Evaluation
Purdue University · Amazon · Arizona State University
RawVLA: Embodied Neural Image Signal Processor For Robotic Manipulation
Sep 29, 2026Shuhong Liu, Heng Zhou, Lingfeng Qian +7Robotic Manipulation Vision-Language-Action Models
UTokyo · D-Robotics · TohokuU +2
Taming VLAs under Robot Execution Errors: Self-Compensation and Stress Testing
Sep 29, 2026Sohyun Lee, Yoonjae Baek, Jaesang Won +5Robotic Control Robot Manipulation Benchmarks
POSTECH · MBZUAI
Disentangling Spurious Correlations in Vision-Language-Action Models via Predicting Domain-Invariant Latent Lookahead
Sep 29, 2026Junghyun Kim, Ngseo Kim, ChungWoo Lee +7Domain Generalization Vision-Language-Action Models
OpenMind, San Francisco, CA, USA · Seoul National University, Seoul, Korea · Hyundai Motors, Korea +2
CoRe-VLA: Preserving Cross-View Coordination in VLAs under Camera Shifts
Sep 29, 2026Tianhang Pan, Xuanhao Wang, Yiwen Pang +4Point Cloud Surface Reconstruction Vision-Language-Action Models
Southeast University, Nanjing, China · National Center of Technology Innovation for EDA, Nanjing, China
Where Predictive Supervision Goes Shapes What VLA Policies Learn
Sep 29, 2026Hanseul Kim, Jewon Yeom, Youngjoon Jeong +2Visuomotor Policy Learning Vision-Language-Action Models
Graduate School of Data Science Seoul National University
Do Not Cut When Uncertain: Rejectable and Calibrated Decision Heads for VLA Policies in Robotic Harvesting
Sep 28, 2026Heng ZhangUncertainty Estimation for VLA Models Selective Prediction
Learning to Act under Visual Interruptions with Vision-Language-Action Models
Sep 28, 2026Mingle Jiang, Rui Xu, Yunke Wang +1Vision-Language-Action Models Vision-Based Robot Control
School of Computer Science, The University of Sydney
ActionUNet: Improving Robustness of VLA Models with Efficient Multi-scale Fine-tuning
Sep 28, 2026Di Zhu, Ziheng Yan, Fang WanRobotic Control Efficient VLA Models
University of Chinese Academy of Sciences
RoboIRGBench: Benchmarking Implicit Referential Grounding in Vision-Language-Action Models
Sep 28, 2026Aernaer Akelijiang, Jiannan Li, Zhineng Chen +2Language-Conditioned Robot Manipulation Vision-Language-Action Models
Singapore Management University · Fudan University
TLC-DiT: Task-Aligned Local Visual Conditioning for Robust Multitask Robot Manipulation
Sep 28, 2026Xianbo Cai, Hideyuki Ichiwara, Zihang Wang +2Language-Conditioned Robot Manipulation Multi-Task Robotic Manipulation
Department of Intermedia Art and Science, Waseda University, Tokyo, Japan · SB Intuitions Corp., Tokyo, Japan · Department of Electronic and Physical Systems, Waseda University, Tokyo, Japan +2

Oct 8, 2026, cs.CVJ/K move · Enter open · S save

VersaCamVLA: Camera-Configurable VLA Policies for Robotic Manipulation

Boyao Han, Chen Shi, Jingjing Qian, ZhuoTan Tian+1

The Chinese University of Hong Kong, Shenzhen · Shenzhen Loop Area Institute · Harbin Institute of Technology, Shenzhen

Vision-Language-Action Models Robotic Manipulation Robustness of VLA Models Multi-View Learning

Open paper AskPDF arXiv

Vision-Language-Action (VLA) models have emerged as powerful foundations for robotic manipulation, but their reliance on fixed camera configurations during training makes them brittle to changes in camera count or pose during deployment. To overcome these limitations, we propose VersaCamVLA, a camera-configurable framework that decouples camera-set representation from action learning. VersaCamVLA learns a unified scene-token interface that maps an arbitrary, variable set of posed RGB views into fixed-size latent scene tokens. This is achieved via multi-signal target-view prediction and Wrist-Augmented Pose Sampling (WAPS), which leverages natural wrist-camera motion for free pose diversity. At deployment, a lightweight spatial encoder injects these compact scene tokens into a pretrained base VLA as a supplementary visual condition, requiring no explicit 3D sensing or novel-view rendering. Experiments on RoboTwin, LIBERO, and a real-robot platform demonstrate that VersaCamVLA consistently outperforms prior VLA methods and direct multi-view baselines, maintaining robust performance across varying camera counts and unseen camera poses.

Momentum

Related topics

Latest papers 142