Vision-Language-Action Models

Also known as VLA

These models combine vision-language backbones with action generators that produce continuous motion or discrete action tokens, often in chunks and with proprioceptive input. They are commonly trained on robot demonstrations, with flow-matching and diffusion policies, reinforcement fine-tuning, and predictive world models used to improve control and planning. Research spans tabletop and bimanual manipulation, mobile and aerial navigation, autonomous driving, and humanoid control, evaluated on benchmarks such as LIBERO, CALVIN, RoboTwin, and driving simulators. A central challenge is making broad visual and language competence translate into reliable closed-loop behavior under new objects, viewpoints, embodiments, delays, and safety constraints; benchmark success can still conceal weak instruction grounding and sim-to-real failures.

Latest papers

1,154 papers249 papers in the last four weeks, up 144% on the four weeks before. 1.5% of all new papers.

EmbodiedSkills: World Action Model-augmented Cascaded Skills for Vision-Language-Action Agent
Sep 1, 2026Wei Wang, Wenqiao Zhang, Yutong Lin +14Robotic Control Large Language Model-Based Robot Planning
College of Computer Science and Technology, Zhejiang University · Nanjing University of Aeronautics and Astronautics · Cornell University +3
REFACTOR-VLA: Unsupervised Library Learning of Typed Motor Programs
Sep 1, 2026Riyaaz Shaik, Chandru VenkataramanRobot Skill Learning Program Synthesis
Apple
Knowing When to Stop: Adaptive Action Chunking via Internal Cross-Attention Dynamics in VLAs
Sep 1, 2026Runze Xu, Xiaolong Shan, Shuang Dai +2Efficient VLA Model Inference Robotic Manipulation
Tsinghua University
LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation
Aug 31, 2026Shaoan Wang, Aocheng Luo, Fei Huang +17Embodied Navigation Cross-Embodiment Robot Learning
Light Origins Team
Temporal Forcing: 4D Representation Alignment for Vision-Language-Action Models
Aug 31, 2026Xingyu Ding, Yuzhong Zhao, Chunhai Zhao +3Representation Learning Robotic Manipulation
Nanjing University, Nanjing, China · Institute of Automation, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China
CometVLA: Co-Training on an Embodied Data Pyramid towards Physical Understanding
Aug 31, 2026Hanwen Wan, Dafeng Chi, Linbo Zhai +6Language-Conditioned Robot Manipulation Embodied QA
1JD Explore Academy, China. · 5South China University of Technology, China. · School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China. +3
Rethinking Language's Role in Efficient VLA for Autonomous Vehicles: Toward Smarter, Trustworthy Driving
Aug 31, 2026Tongfei Guo, Lili SuVLMs for Autonomous Driving Efficient VLA Model Inference
Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA.
Training-Free Action Correction for VLA Model Failures via Language Feedback
Aug 30, 2026Owen Kwon, Pablo Ortega-Kral, Arthur Bucker +1Vision-Language-Action Models Test-Time Adaptation of VLA Models
Biomedical Engineering, Carnegie Mellon University, Pittsburgh PA 15213, USA. · Robotics Institute, Carnegie Mellon University, Pittsburgh PA 15213, USA.
AcrossWAM1.0:A Modular Latent World-Action Stack for Compact Robot Policies
Aug 30, 2026Yafei Zhang, Nan WuEfficient VLA Model Inference Vision-Language-Action Models
Across Physical AI, Beijing, China
DriftingVLA: Native One-Step Vision-Language-Action Generation via Per-Dimension Temporal Drifting
Aug 30, 2026Yuxuan Gao, Shiqi Zhang, Yedong Shen +6Efficient VLA Model Inference Visuomotor Policy Learning
University of Science and Technology of China, Hefei 230026, China. · LYNSENSE, Shanghai, China.
AGM: Achievement-Grounded Memory for Closed-Loop Agents with Frozen VLA Policies
Aug 30, 2026Hongbo Gao, Zeyu Ni, Xin Wen +4Memory-Augmented VLMs Robotic Manipulation
Harbin Institute of Technology · The University of Sydney · StellarEdge AI
SMILE: Smooth Motion for Improved Long-Horizon VLA Execution
Aug 29, 2026Jongwoo Park, E-Ro Nguyen, Kanchana Ranasinghe +3Vision-Language-Action Models Robot Motion Generation
Stony Brook University · Salesforce AI Research
AdaVLA: Adaptive Step Flow Matching for Training-free Acceleration of Vision-Language-Action Models
Aug 29, 2026Sunghwan Han, Youngtae Han, Youngmin YiFlow Matching Vision-Language-Action Models
Dept. of Artificial Intelligence, Sogang University, Seoul, 04107, Republic of Korea
DREAM: Deployment-Time Demonstration Generation via Real-to-Sim for Scalable Policy Adaptation
Aug 29, 2026Makoto Sato, Tatsuya Matsushima, Yutaka Matsuo +1Synthetic Data Generation for Robotics Data-Efficient Robot Learning
The University of Tokyo, Tokyo, Japan.
DeicticVLA: Unifying Instruction Modes Based on Language and Deictic Gestures in a Single VLA
Aug 28, 2026Kango Yanagida, Tatsuya Aoki, Yuichiro Yoshikawa +1Vision-Language-Action Models Instruction Generalization in VLA Models
Dept. of Systems Innovation, Graduate School of Engineering Science, The University of Osaka, Japan. · International Research Center for Neurointelligence, The University of Tokyo, Japan.
PHR-VLA: Planning Horizon Reasoning for Vision-Language-Action Models
Aug 27, 2026Davood Soleymanzadeh, Kaidi Zhang, Zhiyuan Zhang +4Vision-Language-Action Models Reasoning for VLA Models
J. Mike Walker ’66 Department of Mechanical Engineering, Texas A&M University, College Station, TX 77843, USA · Department of Industrial Engineering, Purdue University, West Lafayette, IN 47907, USA · Zachry Department of Civil and Environmental Engineering, Texas A&M University, College Station, TX 77843 USA
Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models
Aug 27, 2026Senqiao Yang, Chengyao Wang, Yuxin Chen +13Robot Foundation Models Cross-Embodiment Robot Learning
TemporalFlow-VLA: Learning Physically Grounded Execution History for Long-Horizon Robot Manipulation
Aug 27, 2026Jiarui Yang, Yehao Lu, Yuning Su +9Robot Learning Long-Horizon Robotic Manipulation
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China. · Zhejiang University, Hangzhou, China. · Simon Fraser University, Burnaby, BC, Canada. +1
FLARE: A Failure-Aware Framework for Autonomous Correction and Recovery in Visual-Language Robotic Manipulation
Aug 27, 2026Ganlong Zhao, Zijia Tang, Xingping Chen +3Robot Failure Recovery Robustness of VLA Models
The Chinese University of Hong Kong · Centre for Perceptual and Interactive Intelligence · Duke University +5
TrapVLA: Trapping Vision-Language-Action Models in Configured Failure Modes
Aug 27, 2026Jun-Hui Liu, Kun-Yu Lin, Yi-Lin Wei +9Adversarial Attacks on VLA Models Vision-Language-Action Models
School of Computer Science and Engineering, Sun Yat-sen University, China · Pengcheng Laboratory, China · The University of Hong Kong, China +1
StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models
Aug 26, 2026Zhe Liu, Jinghua Hou, Yuxiang Lu +7Vision-Language-Action Models Reasoning for VLA Models
The University of Hong Kong · ACE Robotics
One Policy, Many Embodiments: Unified Camera-Centric Action Geometry Pre-training for Heterogeneous Embodied Manipulation
Aug 26, 2026Xiaomi Embodied Intelligence Team, University of Macau, : +21Robot Learning Cross-Embodiment Robot Learning
Xiaomi Embodied Intelligence Team · University of Macau
MA-VLA: Multi-Arm Vision-Language-Action Model for Collaboration and Compositional Generalization
Aug 26, 2026Zaibin Zhang, Junlan Xiao, Zhongbo Zhang +11Vision-Language-Action Models Instruction Generalization in VLA Models
Dalian University of Technology · Shanghai Jiao Tong University · The Chinese University of Hong Kong, Shenzhen +4
LM-X: Explainable Vision--Language--Action Modeling via Progress, Event, and Uncertainty Prediction
Aug 26, 2026Jin Lou, Zhiyuan Jing, Xupeng Wang +21Robotic Control Uncertainty Estimation for VLA Models
Humanoid Robot (Shanghai) Co., Ltd. · E-surfing Digital Life Technology Co., Ltd., China Telecom
GaussianDream++: Efficient 3D Gaussian World Modeling for Robotic Manipulation
Aug 26, 2026Yuqing Jiang, Zijian Zhang, Weitao Zhou +8World Models for Robotics Robotic Manipulation
University of Chinese Academy of Sciences · Institute of Automation, Chinese Academy of Sciences · Tuojing Intelligence +7
RA-VLA: Retrieval-Augmented VLA for Test-Time Adaptation
Aug 26, 2026Sanghwan Jang, Minjin Jeon, Minsoo Kim +3Test-Time Adaptation of VLA Models Vision-Language-Action Models
Department of Computer Science and Engineering, POSTECH, Pohang, South Korea · Graduate School of Artificial Intelligence, POSTECH, Pohang, South Korea
V-Link: Recovering Lost Visual Representations in Action DiT for Vision-Language-Action Models
Aug 26, 2026Yehao Lu, Jiarui Yang, Yuning Su +10Vision-Language-Action Models VLMs for Robotics
Zhejiang University · AGIBOT · The Hong Kong University of Science and Technology (Guangzhou) +1
Gripper-aware Vision Language Action Models
Aug 25, 2026Hanyi Zhang, Zihong Luo, Tianyu Li +16Vision-Language-Action Models VLMs for Robotics
University of Liverpool, UK · Mohamed bin Zayed University of Artificial Intelligence, UAE · Indian Institute of Science, India +5
GaussVLA: Geometry-Aware Spatial Reasoning for Vision-Language-Action Model
Aug 25, 2026Md Selim Sarowar, Md Tanvir Islam, Sungho Kim +1Vision-Language-Action Models VLMs for Robotics
Yeungnam University, Republic of Korea · Kyungpook National University, Republic of Korea
PonderPounce: A Pretrained MLLM as an Episode Context Engine for Robot Control
Aug 25, 2026Suhwan Choi, Jaeyoon Jung, Sungkyung Kim +2Robotic Control Language Model-Based Control
Seoul National University · Georgia Institute of Technology

Sep 1, 2026J/K move · Enter open · S save

EmbodiedSkills: World Action Model-augmented Cascaded Skills for Vision-Language-Action Agent

Wei Wang, Wenqiao Zhang, Yutong Lin, Yuqian Yuan+13

College of Computer Science and Technology, Zhejiang University · Nanjing University of Aeronautics and Astronautics · Cornell University+3

Robotic Control Large Language Model-Based Robot Planning Robotics Vision-Language-Action Models

Open paper AskPDF arXiv

Vision-language-action (VLA) policies generate executable robot actions, but plausible proposals can have different consequences for the task. We present EmbodiedSkills, a skill-based agent framework that augments frozen VLA policies with world action models for consequence-aware action selection. The framework defines reusable skills for scene observation, context encoding, candidate generation, consequence prediction, outcome evaluation, candidate comparison, and action execution. Five stages organize their input-output dependencies in a shared feedback loop, accommodating both continuous action chunks and pick-and-place primitives. At each decision point, independently trained world action models predict the latent consequences of a common set of policy proposals. Selection combines their outcome scores and prediction disagreement with a lightweight comparator that estimates the benefit of an alternative from agreement in its predicted effects. The predictive and comparison modules learn from matched-state candidate branches, while the action policy and pretrained observation encoders remain frozen. On MetaWorld MT50 and CLIPort, EmbodiedSkills improves success rates from 76.28% to 78.64% and from 33.94% to 36.83%, respectively. An additional CALVIN evaluation with the frozen FLOWER policy increases five-task-chain success from 77.10% to 77.90%. These results demonstrate the applicability of consequence-aware selection across different policy backends and action representations.