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.

Simple-to-Complex Structured Demonstrations for Vision-Language-Action Learning
Jul 6, 2026Xinchuan Qiu, Yi YuLong-Horizon Robotic Manipulation Robotic Manipulation
Graduate School of Advanced Science and Engineering, Hiroshima University, Higashi-Hiroshima, Japan
VLA Grounder: Language-Conditioning Space Optimization for Black-Box VLA Models
Jul 5, 2026Damir Shodiev, Nikita Kachaev, Alexey K. Kovalev +2Language-Conditioned Robot Manipulation Vision-Language-Action Models
MIRAI · AXXX · MISIS
XS-VLA: Teaching Tiny Vision-Language-Action Models with Spatial Supervision and Demonstration Conditioning
Jul 5, 2026Iok Tong Lei, Ying Jie Yap, Wei Huang +5Robot Policy Learning Language-Conditioned Robot Manipulation
Department of Computer Science and Technology, Tsinghua University, Beijing, China. · National College for Excellent Engineers, Beihang University, Beijing, China. · Independent Researcher +1
Look Before You Leap: Distilling Tree Search into Action Evaluation for Frozen VLA Models
Jul 4, 2026Xinyi Xie, Zican Hu, Zhanyu Liu +7Value Function Estimation Test-Time Scaling
Nanjing University · Australian National University · Institute of Automation, Chinese Academy of Sciences +1
CoRE-VLA: Towards Scalable and Robust Vision-Language-Action Modeling via Conditional Routing of Experts
Jul 4, 2026Haozhe Zhang, Sixian Li, Yifei Zhang +5Multimodal Robustness Language-Conditioned Robot Manipulation
Zhejiang University · Shanghai Innovation Institute · Fudan University +2
WorldBagel: Uncovering the Power of Unified Multimodal Models for Vision-Language-Action-World Modeling
Jul 3, 2026Zelin Zhao, Min Shi, Bo Yuan +5World Models for Robotics Unified Multimodal Models
Georgia Institute of Technology
HiMe: Hierarchical Embodied Memory for Long-Horizon Vision-Language-Action Control
Jul 3, 2026Li Ji, Siyin Wang, Pengfang Qian +5Long-Horizon Robotic Manipulation Vision-Language-Action Models
1Fudan University · 2Shanghai Innovation Institute · 3East China Normal University
Feeling the Unexpected: ResTacVLA for Contact-Rich Manipulation via Residual Tactile Representation
Jul 3, 2026Pengwei Zhang, Bin Xie, Ce Hao +5Contact-Rich Robotic Manipulation Visuo-Tactile Representation Learning
Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China · Zhongguancun Academy, Beijing 100094, China · Dexmal, Beijing 100096, China
Present but Not Remembered: Auditing How Frozen VLAs Encode, Deploy, and Steer Visual History
Jul 3, 2026Chih-Ting Liao, Xin CaoVLM Interpretability Vision-Language-Action Models
University of New South Wales
AnchorVLA: Bridging Discrete Decisions and Continuous Trajectories for Vision-Language-Action Planning
Jul 3, 2026Qi Liu, Yabei Li, Hongsong Wang +2Hierarchical Planning Vision-Language-Action Models
School of Vehicle and Mobility, Tsinghua University, Beijing 100084, China · State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing 100084, China · School of Computer Science and Engineering, Southeast University, Nanjing 210096, China +2
Exp2VLA: Enabling Vision-Language-Action for Drone Navigation from Expert Demonstrations
Jul 3, 2026Van Huyen Dang, Kabilesh Rajendran, Erdi Sayar +1UAV Navigation Vision-Language-Action Models
Automatic Control Group Paderborn University Paderborn, Germany
DREAMSTEER: Latent World Models Can Steer VLA Policies During Deployment Without Any Finetuning
Jul 3, 2026Hanchen Cui, Sergio Arnaud, Arjun Majumdar +5World Model-Based Planning Robotic Manipulation
1Fundamental AI Research (FAIR), Meta · University of Minnesota Twin Cities
Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots
Jul 2, 2026Ling Xu, Chuyu Han, Borui Li +6Efficient Neural Network Inference Efficient VLA Model Inference
Southeast University · Nanjing University · Microsoft Research +1
Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs
Jul 2, 2026Junhao Shi, Siyin Wang, Xiaopeng Yu +3Self-Supervised Pre-Training Efficient VLA Models
1Fudan University · 2Shanghai Innovation Institute
The Moving Eye: Enhancing VLA Spatial Generalization via Hybrid Dynamic Data Collection
Jul 2, 2026Jincheng Tang, Yilong Zhu, Zhengyuan Xie +2Generalization in Robotic Manipulation Robotic Manipulation
Lion Rock AI Lab, China Merchants Research Institute of Advanced Technology. · The Hong Kong University of Science and Technology. · Nankai University.
CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation
Jul 2, 2026Haokun Liu, Zhaoqi Ma, Yicheng Chen +5Robotic Control Robot Navigation
Dragon Lab, Department of Mechanical Engineering, The University of Tokyo
Bridge-WA: Learning Action-Relevant World Dynamics for Robotic Manipulation
Jul 2, 2026Yongjie Bai, Mingtong Dai, Zhouxia Wang +5World Models for Robotics Language-Conditioned Robot Manipulation
Sun Yat-sen University · Pengcheng Laboratory · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences +1
Guided Action Flow: Value-Guided Sampling for Frozen Vision-Language-Action Policies
Jul 2, 2026Liuhaichen Yang, Zhuang Jiang, Chenchao Sheng +8Robotic Manipulation Vision-Language-Action Models
Department of Computer Science, University College London. · Department of Mechanical Engineering, University College London.
Teaching Vision-Language-Action Models What to See and Where to Look
Jul 2, 2026Yuguang Yang, Canyu Chen, Zhewen Tan +10End-to-End Autonomous Driving VLM Distillation
School of Electronic Information Engineering, Beihang University · Institute for AI Industry Research (AIR), Tsinghua University · National College for Excellent Engineers, Beihang University +5
VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment
Jul 2, 2026Guoyang Xia, Fengfa Li, Hongjin Ji +4Vision-Language-Action Models VLMs for Robotics
Li Auto Inc. · School of Artificial Intelligence, Beijing University of Posts and Telecommunications · The Chinese University of Hong Kong, Shenzhen
Neuro-Symbolic Safety Guidance for Vision-Language-Action Models via Constrained Flow Matching
Jul 1, 2026William English, Hao Zheng, Rickard EwetzCollision Avoidance Flow Matching
FurnitureVLA: Learning Long-Horizon Bimanual Furniture Assembly with Vision-Language-Action Model
Jul 1, 2026Chenyang Ma, Yue Yang, Radu Corcodel +4Long-Horizon Robotic Manipulation Bimanual Robotic Manipulation
Mitsubishi Electric Research Laboratories, Cambridge, MA, USA · University of Oxford, Oxford, UK
DynaWM: A Base-VLA-Guided World Foundation Model for Moving-Object Manipulation
Jul 1, 2026Chongkei Chang, Zhidong DengWorld Models for Robotics Vision-Language-Action Models
Department of Computer Science and Technology, THUAI, Tsinghua University, Beijing 100084, China
Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts
Jul 1, 2026Taewook Kang, Taeheon Kim, Donghyun Shin +1Domain Adaptation Vision-Language-Action Models
Seoul National University · ECE, IPAI and ASRI in SNU
Unleashing More Actions via Action Compositional Training for VLA Models
Jul 1, 2026Kai Peng, Jie Lu, Xiaojiang PengSynthetic Data Augmentation Synthetic Data Generation for Robotics
School of Artificial Intelligence Shenzhen Technology University Shenzhen, China
Human-as-Humanoid: Enabling Zero-Shot Humanoid Learning from Ego-Exo Human Videos with Human-Aligned Embodiments
Jun 30, 2026Xiaopeng Lin, Ruoqi Yang, Shijie Lian +14Humanoid Robot Control Cross-Embodiment Robot Learning
The Hong Kong University of Science and Technology (Guangzhou) · DeepCybo · ZGCA +4
Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models
Jun 30, 2026Lang Cao, Renhong Chen, Luyi Li +3Robot Skill Learning Efficient VLA Models
Zioneer Robot Team
UniTacVLA: Unified Tactile Understanding and Prediction in Vision Language Action Models
Jun 30, 2026Xidong Zhang, Yichi Zhang, Jiaxin Shi +5Contact-Rich Robotic Manipulation Visuo-Tactile Representation Learning
Harbin Institute of Technology · Great Bay University · Daimon Robotics +3
Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptation
Jun 30, 2026Fengnian Zhang, Tao Huang, Siyu Xu +2VLM Adaptation Vision-Language-Action Models
Computer Network Information Center, Chinese Academy of Sciences · University of Chinese Academy of Sciences · School of Computer Science, Shanghai Jiao Tong University +1
3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance
Jun 30, 2026Dongyoon Hwang, Byungkun Lee, Dongjin Kim +7Robotic Control Vision-Language-Action Models
Kim Jaechul Graduate School of AI, KAIST, Seoul, Republic of Korea · Graduate School of Artificial Intelligence, POSTECH, Pohang, Republic of Korea · Holiday Robotics, Seoul, Republic of Korea +1

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

Simple-to-Complex Structured Demonstrations for Vision-Language-Action Learning

Xinchuan Qiu, Yi Yu

Graduate School of Advanced Science and Engineering, Hiroshima University, Higashi-Hiroshima, Japan

Long-Horizon Robotic Manipulation Robotic Manipulation Vision-Language-Action Models Robot Imitation Learning

Open paper AskPDF arXiv

Vision-Language-Action (VLA) models have demonstrated strong capabilities in robotic manipulation by integrating visual perception, language understanding, and robot action generation. Existing research has primarily focused on improving model architectures, training strategies, and dataset scale, while little attention has been paid to how demonstrations are collected and organized. We identify demonstration organization as a fundamental yet overlooked aspect of imitation learning, as it directly affects policy learning efficiency, training stability, and policy generalization. To address this gap, we propose a simple-to-complex structured demonstration collection strategy for VLA learning using a dual-arm robotic platform. Our approach systematically organizes data through three general principles: (i) decomposing complex manipulation tasks into progressively learnable sub-skills, (ii) standardizing the interaction environment to reduce unnecessary variability, and (iii) organizing demonstrations according to progressively increasing task complexity. This structured design enables VLA models to first acquire fundamental manipulation skills before learning increasingly complex task compositions, facilitating more effective learning of long-horizon manipulation tasks. We evaluate the proposed strategy on two representative robotic manipulation tasks: block grasping and sorting, and towel folding. Experimental results show consistent improvements in task success rate and training stability compared with the baseline method of directly collecting end-to-end complete task trajectories. These findings highlight demonstration organization as a previously underexplored but important factor in VLA learning and provide practical insights into efficient skill acquisition, scalable dataset construction, and long-horizon robotic manipulation.