Vision-Language-Action Models

Also known as VLA

Follow this topic Ask about this topic

Latest papers 1,140

249 papers in the last four weeks, up 144% on the four weeks before. 1.5% of all new papers.

All topics

Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulation
Jun 2, 2026Nan Sun, Yuan Zhang, Yongkun Yang +10Long-Horizon Robotic Manipulation CoT Reasoning
Tsinghua University · Xiaomi Robotics · Peking University +6
PHASER: Phase-Aware and Semantic Experience Replay for Vision-Language-Action Models
Jun 2, 2026Ziyang Chen, Shaoguang Wang, Weiyu Guo +5Continual Learning for VLA Models Robotic Manipulation
Thrust of AI, HKUST(Guangzhou), Guangzhou, China · AI2 Robotics, Shenzhen, China
Partially Observable Adversarial Patch Attacks on Vision-Language-Action Models in Robotics
Jun 2, 2026Xiaofei Wang, Mingliang Han, Tianyu Hao +3VLM Robustness Adversarial Patch Attacks
Department of Automation, University of Science and Technology of China, Hefei, China · SmartMore Corporation · Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, China +2
OpenEAI-Platform: An Open-source Embodied Artificial Intelligence Hardware-Software Unified Platform
Jun 2, 2026Jinyuan Zhang, Luoyi Fan, Leiyu Wang +4Robotic Control Robotics
1Shanghai Innovation Institute · 2Huazhong University of Science and Technology · 3Shanghai Jiao Tong University +1
Dive into the Scene: Breaking the Perceptual Bottleneck in Vision-Language Decision Making via Focus Plan Generation
Jun 2, 2026Boyuan Xiao, Bohong Chen, Yumeng Li +3Vision-Language-Action Models VLMs for Robotics
State Key Lab of CAD&CG, Zhejiang University, China · Baiont Quant, China · Zhejiang Key Laboratory of Intelligent Medical Decision Support, China
GeoAlign: Beyond Semantics with State-Guided Spatial Alignment in VLA Models
Jun 2, 2026Yizhi Chen, Zhanxiang Cao, Xinyi Peng +14Visuomotor Policy Learning Geometric Representation Learning
Tongji University · Shanghai Innovation Institute · Shanghai Jiao Tong University +5
TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Models
Jun 2, 2026Wenbo Zhang, Jianxiong Li, Shuai Yang +4Test-Time Adaptation Test-Time Adaptation of VLMs
ByteDance Seed · The University of Adelaide · Tsinghua University +3
Cosmos 3: Omnimodal World Models for Physical AI
Jun 1, 2026NVIDIA, :, Aditi +293Unified Multimodal Models World Models
SeeTraceAct: Visibility-Aware Latent Planning from Cross-Embodiment Demonstration Videos
Jun 1, 2026Jaehyeon Son, Junhyun Kim, Kyle Kam +7Robot Skill Learning Generalization in Robotic Manipulation
Georgia Institute of Technology · Allen Institute for AI · Johns Hopkins University +1
See Less, Specify More: Visual Evidence Budgets for Generalizable VLAs
Jun 1, 2026Yueh-Hua Wu, Tatsuya Matsushima, Kei OtaVisuomotor Policy Learning Vision-Language-Action Models
AIRoA
Intercepting the Future: Latent-Space Predictive World Model for Dynamic VLA Manipulation
Jun 1, 2026Shahram Najam Syed, Arthur Jakobsson, Haoran Hao +1World Models for Robotics Robotic Manipulation
Robotics Institute, Carnegie Mellon University, Pittsburgh, USA
Towards Precise Intent-Aligned VLA Aerial Navigation via Expert-Guided GRPO
Jun 1, 2026Tianyang Chen, Wenjun Li, Xin zhou +2UAV Navigation Group Relative Policy Optimization
1Zhejiang University · 2Differential Robotics
FATE-VLA:Failue-aware test generation for vision-language-action models
Jun 1, 2026Arusa Kanwal, Pablo Valle, Shaukat Ali +1VLM Evaluation Vision-Language-Action Models
Mondragon University Mondragon, Spain · Simula Research Laboratory Oslo, Norway
RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA Models
Jun 1, 2026Bin Yu, Yao Zhang, Haishan Liu +9Language-Conditioned Robot Manipulation Vision-Language Grounding
1HIT · 2ZGCA · 3ZGCI +6
WALL-WM: Carving World Action Modeling at the Event Joints
Jun 1, 2026Shalfun Li, Victor Yao, Charles Yang +28World Model Learning Vision-Language-Action Models
X Square Robot Team
Co-training with Ego-centric Video and Demonstration for Robot Navigation Task
Jun 1, 2026Shoya Kuno, Yumo Ouchi, Kanata SuzukiMobile Robotics Robot Navigation
Spatial Robotics Research Center, Fujitsu Limited., Kanagawa 211-8588, Japan.
The Lie We Tell: Correcting the Euclidean Fallacy in Vision Language Action Policies via Score Matching on Tangent Space
Jun 1, 2026Bing-Cheng Chuang, I-Hsuan Chu, Bor-Jiun Lin +3Lie Group Methods Robotic Manipulation
Department of Computer Science and Information Engineering & Artificial Intelligence Center of Research Excellence, National Taiwan University, Taipei, Taiwan · Institute of Artificial Intelligence Innovation, National Yang Ming Chiao Tung University, Hsinchu, Taiwan · Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan.
LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting World
May 31, 2026Hojune Kim, Timothy Chen, Jiankai Sun +4Humanoid Loco-Manipulation Robotics Simulation
Stanford University
Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?
May 31, 2026Liyang Li, Muzhi Zhu, Zhiyue Zhao +53D Foundation Models Visual Spatial Reasoning
Zhejiang University
OneVLA: A Unified Framework for Embodied Tasks
May 31, 2026Lingfeng Zhang, Xiaoshuai Hao, Yingbo Tang +10Vision-Language Navigation Robotic Manipulation
1Tsinghua University · 3Xiaomi EV · Institute of Automation, Chinese Academy of Sciences +3
Beyond Task Success: Behavioral and Representational Diagnostics for WAM and VLA
May 31, 2026Hung Mai, Bin Zhu, Tuan DoWorld Models for Robotics Robotic Policy Evaluation
National Economics University, Vietnam · N2TP Technology · Singapore Management University +1
Make Your VLA More Robust Without More Data By Interleaving Motion Planning
May 31, 2026Dan BW Choe, Sundhar Vinodh Sangeetha, Samuel Coogan +1VLM Robustness Long-Horizon Robotic Manipulation
Georgia Institute of Technology, Atlanta, GA, USA
Threading Optimization for Vision-Language-Action Model Inference in Low-Cost Smart Agricultural Manipulation
May 31, 2026Keith Truongcao, Christopher Nhu, Zijian An +3Efficient VLA Model Inference Robotic Manipulation
Department of Electrical Engineering, Drexel University, Philadelphia, USA
SafeVLA-Bench: A Benchmark for the Success-Safety Gap in Vision-Language-Action Models
May 30, 2026Jialiang Fan, Weizhe Xu, Zijun Wang +3Robot Safety Robotic Manipulation
University of Notre Dame · University of Pennsylvania
PaCo-VLA: Passivity-Shielded Compliance Prior for Contact-Rich Vision-Language-Action Manipulation
May 30, 2026Haofan Cao, Zhaoyang Li, Zhichao You +2Contact-Rich Robotic Manipulation Admittance Control
Southwest Jiaotong University
Closed-Loop Neural Activation Control in Vision-Language-Action Models
May 29, 2026Abhijith Babu, Ramneet Kaur, Nathaniel D. Bastian +5Vision-Language-Action Models Activation Steering
Florida International University · SRI International · United States Military Academy +2
Per-Group Error, Not Total MSE: Fine-Tuning Vision-Language-Action Models for 11-DoF Mobile Manipulation
May 29, 2026Pau Montagut Bofi, Mario García Blasco, Tessa Pulli +1Mobile Manipulation VLM Adaptation
Vision for Robotics Lab (V4R), TU Wien, Vienna, Austria
Continuous Reasoning for Vision-Language-Action
May 29, 2026Yueh-Hua Wu, Tatsuya Matsushima, Kei OtaVision-Language-Action Models VLMs for Robotics
AIRoA
DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable Manipulation
May 29, 2026Taiyi Su, Jian Zhu, Tianjian Wang +9Language-Conditioned Robot Manipulation Deformable Object Manipulation
1AIRC, Midea Group · 2Tongji University
DriveMA: Driving Vision-Language-Action Models with verifiable Meta-Actions
May 29, 2026Weicheng Zheng, Yixin Huang, Qiao Sun +2VLMs for Autonomous Driving Autonomous Driving
1Shanghai Qi Zhi Institute · 3Tongji University · 2IIIS Tsinghua University

Jun 2, 2026J/K move · Enter open · S save

Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulation

Nan Sun, Yuan Zhang, Yongkun Yang, Wentao Zhao+9

Tsinghua University · Xiaomi Robotics · Peking University+6

Long-Horizon Robotic Manipulation CoT Reasoning Generalization in Robotic Manipulation Robotic Manipulation Vision-Language-Action Models

Open paper AskPDF arXiv

Embodied chain-of-thought (CoT) aims to bridge linguistic reasoning and robotic control, but its effective form and integration strategy remain underexplored. In this paper, we revisit embodied CoT for vision-language-action (VLA) models at large scale. We construct the largest embodied CoT corpus to date, comprising 978,743 trajectories, 226.3M samples, and 2592.5 hours of robot data. Through extensive experiments, we find that effective embodied CoT should ground high-level semantic understanding into concrete action guidance, such as end-effector movement descriptions and image-space trajectories, while high-level reasoning alone brings only marginal gains. We further show that explicit CoT does not scale reliably when used as an autoregressive action prefix, as it suffers from compounding inference errors and unstable reasoning-action coupling. To address these limitations, we propose ERVLA, a VLA model that uses embodied CoT as representation-shaping supervision rather than mandatory test-time reasoning. ERVLA is trained with a reasoning-dropout strategy, enabling the model to absorb rich reasoning traces during training while predicting actions directly without CoT decoding during inference. This design improves scalability with increasing pre-training data and avoids autoregressive instability. ERVLA achieves state-of-the-art performance on LIBERO-Plus with an 86.9% success rate and reaches 53.2% success rate on VLABench, demonstrating strong out-of-distribution generalization. In real-robot experiments, ERVLA further outperforms competitive state-of-the-art baselines, especially on tasks requiring semantic disambiguation and long-horizon execution.