Flow-Based VLA Models

VLA: Vision-Language-Action

Latest papers

36 papers17 papers in the last four weeks, up 325% on the four weeks before. 0.1% of all new papers.

Meituan-Robotics-0: A Vision-Language-Action Foundation Model for Desktop Manipulation
Nov 5, 2026Meituan Robotics Team, Caicheng Wang, Chen Zhao +35Robot Foundation Models Robotic Manipulation
From Pixels to Actions -- Towards Native Vision-Language-Action Policies
Nov 4, 2026Weichen Fan, Haiwen Diao, Penghao Wu +14Vision-Language-Action Models Robotic Manipulation
S-Lab, Nanyang Technological University · Ropedia · SenseTime Research
Should the Action Expert Train the VLM? Action-Token Supervision and Gradient Routing in Mixture-of-Transformer VLAs
Nov 3, 2026Asher James Hancock, Boyi Li, Yuxiao Chen +6VLA Model Training Flow-Based VLA Models
NVIDIA · Princeton University · Stanford University
Aero-VPA: Few-Step Flow-Matching Control over Non-Reconstructive JEPA Latents for Agile Flight on Edge Hardware
Nov 3, 2026Yeonseok LeeUAV Navigation Closed-Loop Control of VLA Models
SLING AI Inc., Incheon, Republic of Korea
Beyond Policy Patches: Distilling RL Specialists into Vision-Language-Action Policies
Nov 2, 2026Zhennan Jiang, Tingying Xie, Shilong Ji +11Robotic Manipulation Knowledge Distillation
University of Chinese Academy of Sciences · Institute of Automation, Chinese Academy of Sciences · Zhongguancun Academy +3
GatedVLA with Camera-Based Emergency Braking: AlpaSim E2E Closed Loop Challenge Technical Report
Nov 1, 2026Kaneyoshi Hiratsuka, Naoki Takada, Makoto KawanoClosed-Loop Control of VLA Models VLMs for Autonomous Driving
Leap-VLA: High-Rate Robot Control from a Low-Rate VLM Backbone
Oct 31, 2026Lin Yang, Yunjie Shen, Zheyu Li +8Closed-Loop Control of VLA Models Efficient VLA Model Inference
Embodied Algorithm Group, Automation PBU, Leapmotor.
PRIME W0: Physical Priors from World Models for Embodied Manipulation
Oct 29, 2026Huabin Peng, Fagang Jin, Yancong Wei +4Robot Learning Robotic Manipulation
Lumos SZ Lab Team · CUHK · THU +2
SaiVLA-JEPA: Evaluating Future Latent Prediction in JEPA-Conditioned VLA Control
Oct 28, 2026Rufeng Xiao, Ruihao Xiao, Wei Chen +1Closed-Loop Control of VLA Models Temporal Modeling for VLA Models
VLA Research Team, Synthoid.ai
Tokens of Motion: Primitive Motion Learning for Human-Humanoid Skill Transfer
Oct 27, 2026Hanwen Ren, Meng Zheng, Wenzhe Cui +5VLA Model Adaptation Robustness of VLA Models
United Imaging Intelligence, Boston, MA, USA · Purdue University, West Lafayette, IN, USA
VLA-HWBench: Where the Time Goes When VLA Models Run on Edge Hardware
Oct 26, 2026Borui Xu, Hongshi Tan, Wenqi Jiang +4Efficient VLA Model Inference On-Device Inference
National University of Singapore
RynnVLA-Latent: Scaling Robotic Manipulation Foundation Models with 3D-Grounded Latent Actions
Oct 25, 2026Haoyu Zhao, Xingyue Zhao, Zhian Su +11VLA Model Training Robot Foundation Models
DAMO Academy, Alibaba Group · Hong Kong Embodied AI Lab · CUHK +3
Coupling Execution Horizon and Sampling Depth in Flow-Matching VLA Policies
Oct 23, 2026Jiabing Yang, Yuan Xu, Yixiang Chen +13Flow-Based VLA Models Efficient VLA Model Inference
School of Artificial Intelligence, University of Chinese Academy of Sciences. · New Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences. · FiveAges. +2
EgoForesight: Effectively Scaling Policy Learning with Noisy Egocentric Actions
Oct 22, 2026Chubin Zhang, Changyuan Wang, Yirui Wang +7Robot Imitation Learning Robot Learning from Video
Tsinghua University · JD Future Academy · Loopeva +2
When One Step Is Enough: An Empirical Study of Euler Integration in Flow-Matching Policies
Oct 22, 2026Shivakanth Sujit, Luca Nunziante, Rousslan Fernand Julien Dossa +1Flow Matching Efficient VLA Model Inference
Araya Inc., Tokyo
Perceives but Doesn't Brake: A Perception-Action Binding Gap in Reasoning Driving VLAs
Oct 20, 2026Matteo Cercola, Katie Z Luo, Simone Formentin +1Reasoning for VLA Models Safety Evaluation of VLA Models
Politecnico di Milano. · Stanford University. · NVIDIA.
HAF-VLA: Hierarchical Action Flow Framework for Humanoid Vision-Language-Action Control
Oct 19, 2026Langzhe Gu, Chengkai Hou, Meng Li +12Humanoid Robot Control Humanoid Loco-Manipulation
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University · Beijing Innovation Center of Humanoid Robotics · Nankai University +2
VLA-Rolling: Fewer Denoising Steps, Better Control via Adaptive Action Reuse
Oct 18, 2026Sicheng He, Yi Pan, Qiuting Yu +10Efficient VLA Model Inference Flow-Based VLA Models
Zhejiang University
GRASP: Global-Local Representation Alignment and Spatial-Physical Grounding for Bimanual Robotic Manipulation
Oct 16, 2026Zeyuan Ren, Guanxun Zhao, Qi Li +15Bimanual Robotic Manipulation Spatial Grounding for VLA Models
COWARobot Co. Ltd, China. · The Hong Kong Polytechnic University, Hong Kong SAR, China. · Tongji University, Shanghai, China. +4
MambaAct: Efficient Mamba Action Experts for Flow-Matching Vision-Language-Action Models
Oct 16, 2026Khuyen Pham, Tran Nguyen Le, Edoardo Fazzari +1Efficient VLA Model Inference Vision-Language-Action Models
MBZUAI · Technical University of Denmark
Multi-Teacher On-Policy Distillation for Flow-Based Vision-Language-Action Models
Oct 15, 2026Lichao Ni, Yuhan Liu, Pengfei Li +1Flow-Based VLA Models Vision-Language-Action Models
Huawei Technologies Co., Ltd. · Tsinghua University
$Δ$ Flow Matching for Robot Foundation Models
Oct 11, 2026Kuangji Zuo, Tuo An, Xinying Guo +9Flow Matching for Action Generation Robot Foundation Models
MARS Lab, Nanyang Technological University
World-Calibrated Proposal-to-Action Flow for Vision-Language-Action Models
Oct 1, 2026Jie He, Wei Li, Junwen Tong +3World Models for VLA Models Flow-Based VLA Models
Harbin Institute of Technology, Shenzhen · State Key Laboratory of Mobile Network and Mobile Multimedia Technology, ZTE, China · Sun Yat-sen University
RAVEL: Asynchronous Rolling Inference for Flow-Based Vision-Language-Action Models
Sep 28, 2026Yuhan Chen, Ke Yu, Pengfei Liu +3Efficient VLA Model Inference Vision-Language-Action Models
Zhejiang University · Nanyang Technological University
Uncertainty-Gated Exploration Noise Suppresses Task Collapse in Online RL Fine-Tuning of a Flow-Matching Vision-Language-Action Policy
Sep 23, 2026Mehmet Turan Yardımcı, Yunus Emre ÇoğurcuRobot Policy Learning RL Exploration
Karlsruhe Institute of Technology · Çukurova University
Fewer Steps, Better Actions: Rethinking Flow-Matching Inference for VLA Policies
Sep 18, 2026Zhipeng Tang, Xinda Chen, Weining Rao +5Flow-Based VLA Models Efficient VLA Model Inference
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China · Zhongke Haichuan Intelligent
StructRL: Structured Action-Space Exploration for Flow-Based VLAs
Aug 15, 2026Jiarui Yang, Bin Zhu, Jingjing Chen +4Flow-Based VLA Models RL for Robotics
Fudan University · Singapore Management University · Shanghai Artificial Intelligence Laboratory
DRIFT: Derailing Denoising Trajectories of Flow-Matching VLAs with Adversarial Patch Attack
Aug 4, 2026Hoseong Tae, Jong-Seok LeeAdversarial Patch Attacks Adversarial Attacks on VLA Models
School of Integrated Technology, Yonsei University
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.
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

Nov 5, 2026J/K move · Enter open · S save

Meituan-Robotics-0: A Vision-Language-Action Foundation Model for Desktop Manipulation

Meituan Robotics Team, Caicheng Wang, Chen Zhao, Chengpeng Jin+34

Robot Foundation Models Robotic Manipulation Multi-Task Robotic Manipulation Cross-Embodiment Robot Learning Flow-Based VLA Models

Open paper AskPDF arXiv

We present Meituan-Robotics-0 (MR0), a vision-language-action foundation model and embodied-agent system for stationary-base desktop manipulation. MR0 combines 147 million vision-language samples with 15,060 hours of curated robot trajectories spanning 12 embodiments. A three-stage training recipe aligns multimodal representations with robot behavior through discrete action-token pre-training, transfers these priors to continuous cross-embodiment control through flow-matching mid-training, and adapts the policy through real-world post-training. We introduce Rollback, which pairs replaced policy segments with human corrections to provide positive and negative supervision for CFG-DAgger without value learning or advantage labeling. A unified end-effector interface supports heterogeneous embodiments, while asynchronous action-chunk merging maintains smooth execution under variable inference latency. An event-driven agent maintains persistent task events and reassesses plans when progress or feasibility changes, enabling cross-task retrieval and conditional task resumption. MR0 achieves 93.6% success on RoboTwin 2.0 and ranks fifth in the RoboDojo VLA track. Under matched HG-DAgger post-training, MR0 achieves higher average success rate and progress score than

π_{0.5}

across three real-robot tasks. On Ethernet insertion, CFG-DAgger trained with Rollback data reaches 70% success and a progress score of 0.90. Qualitative agent deployments demonstrate cross-task event retrieval and recovery from temporarily unsatisfied task conditions.