Flow Matching for Action Generation

Follow this topic Ask about this topic

Latest papers

21 papers8 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

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
$Δ$ 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
Vision-Predictor-Action: Towards Efficient Embodied AI via Neuro-Symbolic JEPA Predictors
Oct 11, 2026Yeonseok LeeFlow Matching for Action Generation Efficient VLA Models
SLING AI Inc., Incheon, Republic of Korea
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
Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Models
Oct 1, 2026Jiawei Fan, Sifeng Wang, Yuqing Hou +1Flow Matching Robot Foundation Models
Intel Labs China · Midea AI Research
Object-Centric Conditioning for Visuomotor Flow Matching
Sep 21, 2026Jijie Li, Xu Yang, Junhong Zou +4Flow Matching Visuomotor Policy Learning
School of Artificial Intelligence, University of Chinese Academy of Sciences · State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences · Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences +2
SmoLSTM: A Compact Vision-Language-Action Model with Recurrent Memory that Persists
Sep 19, 2026Jan-Gerrit Habekost, Parsa Mastouri Kashani, Connor Gäde +5Flow Matching for Action Generation Vision-Language-Action Models
Knowledge Technology Group, Department of Informatics, University of Hamburg, Hamburg, Germany
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
Agile-WAM: An Agile Tactile World Action Model for Contact-Rich Robot Control
Sep 17, 2026Hanchu Zhou, Brendan Lynch, Raman Goyal +4Robotic Control World Models for Robotics
University of California, Davis, One Shields Avenue, Davis, CA, USA · Analog Devices · Analog Devices, San Jose, CA, USA
Frequency-Conditioned Flow Matching for Vision-Language-Action Models
Sep 9, 2026Haochen Niu, Shengye Dong, Hao Liu +2Flow Matching Robot Motion Generation
AGIBOT · Xi’an Jiaotong University
SLIM-0.5B: Learning Action-Grounded Predictive Latents for Robot Manipulation
Aug 10, 2026Jingkai Wang, Zihan Tang, Gu Zhang +7Latent Dynamics Modeling Language-Conditioned Robot Manipulation
1Fudan University · 2Beijing Academy of Artificial Intelligence · 3Tsinghua University +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.
OpenSPM: An Environment-Transferable Robotic Key Spatial Pose Memory and Closed-Loop High-Frequency Flow-Matching Action Generation Model
Jun 29, 2026Iok Tong Lei, Qingchen Xie, Yifan Wang +2Language-Conditioned Robot Manipulation Generalization in Robotic Manipulation
Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China · Institute for Artificial Intelligence, Tsinghua University, Beijing 100084, China
PAMAE: Phase-Aware-MoE Action Experts Towards Reliable Flow-Matching Vision-Language-Action Policies
Jun 25, 2026Jiayu Yang, Tao Yang, Xiang Chang +3Flow Matching Language-Conditioned Robot Manipulation
Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, China · Department of Computer Science, Aberystwyth University, Aberystwyth, U.K.
Frequency-Aware Flow Matching for Continuous and Consistent Robotic Action Generation
Jun 18, 2026Jianing Guo, Fangzheng Chen, Zihao Mao +12Robotic Control Flow Matching
Beihang University · PKU-Psibot Lab · The Chinese University of Hong Kong +3
Potential-Guided Flow Matching for Vision-Language-Action Policy Improvement
Jun 3, 2026Yunpeng Mei, Jiakai He, Hongjie Cao +12Flow Matching Visuomotor Policy Learning
1Beijing Institute of Technology · 2Tsinghua University · 3The Hong Kong University of Science and Technology (Guangzhou)
MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving
May 12, 2026Yuzhou Huang, Benjin Zhu, Hengtong Lu +6VLMs for Autonomous Driving End-to-End Autonomous Driving
CUHK MMLab · Li Auto · Tsinghua University
CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies
Apr 27, 2026Fan Du, Feng Yan, Jianxiong Wu +8Robotic Control Efficient VLA Model Inference
1Southern University of Science and Technology · 2Xi’an Jiaotong University · 3United Nova Technology +1
HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation
Apr 9, 2026Shuanghao Bai, Meng Li, Xinyuan Lv +14Flow Matching for Action Generation Robotic Control
Beijing Innovation Center of Humanoid Robotics · Xi’an Jiaotong University · Nankai University +1
DM0: An Embodied-Native Vision-Language-Action Model towards Physical AI
Feb 16, 2026En Yu, Haoran Lv, Jianjian Sun +46Flow Matching for Action Generation Vision-Language-Action Models
Learning Robust Visuomotor Policies via Dynamics Alignment
Oct 31, 2025Dohyeok Lee, Jung Min Lee, Munkyung Kim +7Visuomotor Policy Learning Flow-Based Policy Learning
Department of Electrical and Computer Engineering, Seoul National University, Seoul 08826, Korea · Department of Statistics, Korea University, Seoul 02841, Korea

Oct 16, 2026J/K move · Enter open · S save

MambaAct: Efficient Mamba Action Experts for Flow-Matching Vision-Language-Action Models

Khuyen Pham, Tran Nguyen Le, Edoardo Fazzari, Cesare Stefanini

MBZUAI · Technical University of Denmark

Efficient VLA Model Inference Vision-Language-Action Models Flow-Based VLA Models Flow Matching for Action Generation

Open paper AskPDF arXiv

Vision-language-action (VLA) models have shown strong promise for generalist robotic manipulation, but their inference cost remains a major bottleneck for real-time control. This limitation is especially pronounced in flow-matching VLAs such as

π_{0.5}

, where the action expert is evaluated repeatedly during iterative denoising. We introduce MambaAct, an efficient Mamba action expert for flow-matching VLA policies. MambaAct retains the pretrained visual-language prefix encoder of

π_{0.5}

, while replacing its transformer-based action expert with a compact Mamba-based action expert. Within this expert, Mamba serves as the action mixer that models dependencies across the noisy continuous-action sequence. To preserve visual-language conditioning without repeated token-level cross-attention, MambaAct uses a lightweight Context Compressor to map Vision-language model (VLM) prefix tokens into a compact conditioning signal that gates and modulates each Mamba action block. MambaAct uses a

10\times

smaller action expert and reduces flow-matching denoising latency by

64.8\%

on LIBERO and

58.8\%

in real-world deployment, while improving mean LIBERO success by

1.08

percentage points across three independent fine-tuning seeds and maintaining gains on LIBERO-Plus and real-world benchmarks. Our code and model weights are publicly available at https://github.com/giakhuyendihoc/MambaAct.