Multimodal Action Distributions

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 52

All topics

Flowing Faster to Coordinate: One-Step Online Multi-Agent Flow Policies
Oct 1, 2026Zhuoran Li, Yunzhan Li, Xun Wang +2Multi-Agent Reinforcement Learning Flow Policies
Institute for Interdisciplinary Information Sciences, Tsinghua University · Engineering Systems and Design Pillar, Singapore University of Technology and Design
Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Models
Oct 1, 2026Jiawei Fan, Sifeng Wang, Yuqing Hou +1Meanflow Multimodal Action Distributions
Intel Labs China · Midea AI Research
Diffusion-2BC: Hybrid Diffusion and Regression Training for Offline Behavior Cloning in Autonomous Driving
Sep 29, 2026Bruno Maciel Machado, Eric Aislan AntoneloBehavior Cloning Diffusion Policies
Department of Automation and Systems Engineering, Graduate Program in Automation and Systems Engineering, Federal University of Santa Catarina, Florianópolis, Santa Catarina, Brazil
QAMM: Adjoint MeanFlow Matching for Few-Step Offline Reinforcement Learning
Sep 28, 2026Yuehu Gong, Shutong Ding, Mokai Pan +4Flow Policies Meanflow
School of Data Science, Fudan University · ShanghaiTech University · Shanghai Innovation Institute
Faster Visuomotor Policy Learning on Action Manifolds via Riemannian MeanFlow
Sep 24, 2026S. Talha Bukhari, Austin Garrett, Yi Wei +3Flow Policies Multimodal Action Distributions
Department of Computer Science, Purdue University, West Lafayette, IN 47907, USA
JAMB: Joint Action-Motion Diffusion for Bimanual Manipulation
Sep 21, 2026Chuyang Xiao, Peilin Meng, David HeldBimanual Manipulation Multimodal Action Distributions
Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA. · University of Michigan, Ann Arbor, MI 48109, USA.
Learning to Plan in Human-Robot Collaboration: Multimodal Reinforcement Learning for Adaptive Interaction
Sep 21, 2026Afagh Mehri Shervedani, Siyu Li, Natawut Monaikul +3Human-Robot Collaboration Scalable Robot Learning
University of Illinois Chicago, Chicago, IL 60607 USA · California State University Channel Islands
M $^3$ P-R1: Reinforcement Learning for Large Language Model Guided Multi-Modal Motion Planning via MIP Code Generation
Sep 16, 2026Xingpeng Sun, Zherong Pan, Kai Cheng +3Multimodal Action Distributions Mixed-Integer Programming
Purdue University United States · LightSpeed Studios United States
Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport
Sep 14, 2026Jaehun Shon, Jinha Choi, Jongwook Jeon +1Flow Policies Multimodal Action Distributions
Department of Artificial Intelligence, Yonsei University
Refinement-based Flow Policy Optimization
Sep 14, 2026Bumgeun Park, Hyukjun Yang, Donghwan LeeFlow Policies Distributional Reinforcement Learning
Korea Advanced Institute of Science and Technology (KAIST)
IMLE-VLA: Fast Single-Step Action Generation for Vision-Language-Action Policies
Sep 11, 2026Kian Hosseinkhani (Simon Fraser University), Qinhe Peng (University of Pennsylvania), George Shramko (Simon Fraser University) +7Action Generation Multimodal Action Distributions
Simon Fraser University · University of Pennsylvania · Alberta Machine Intelligence Institute (Amii) +1
MoPA: Coordinated Mobile Manipulation via Subsystem-Specific Perception Alignment
Sep 10, 2026Guangyu Chen, Qiwei Liang, Shaolong Zhu +7Perception Pipeline Multimodal Action Distributions
1THU · 2Xspark AI · 3HKUST (GZ) +1
DriftingVLA: Native One-Step Vision-Language-Action Generation via Per-Dimension Temporal Drifting
Aug 30, 2026Yuxuan Gao, Shiqi Zhang, Yedong Shen +6Generalist Vision--Language--Action Action Generation
University of Science and Technology of China, Hefei 230026, China. · LYNSENSE, Shanghai, China.
Discovering Diverse Planning Policies for Multimodal Embodied Agents with Quality-Diversity Optimization
Aug 9, 2026Pengfei Xu, Yong Liu, Xiaoya Nan +2Multimodal Agents Multi-Agent Planning
School of Artificial Intelligence, Nanjing University of Information Science and Technology Nanjing, Jiangsu, China
HCPG-Flow:Hierarchical Contact-Progress Guidance for Flow-Policy Robot Manipulation
Jul 20, 2026Guanghu Xie, Mingxu Li, Shuo Zhang +5Multimodal Action Distributions Robotic Manipulation
State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin 150001, Heilongjiang, China
SegDiff: Segmented Trajectory Diffusion for Consistent and Adaptive Robot Manipulation
Jul 13, 2026Haidong Cao, Wenjun Cao, Quanhao Li +5Visuomotor Policy Imitation Learning
Institute of Trustworthy Embodied AI, Fudan University, China · Shanghai Key Laboratory of Multimodal Embodied AI, China
VINE: Taming Generative Control Policies for Reinforcement Learning
Jul 11, 2026Rushuai Yang, Zhuo Han, Houlin Li +10Flow Policies Generative Control Policies
1AgiBot · 3Peking University · 2The Hong Kong University of Science and Technology
Source-Lifted Flow Matching for Intervenable Multimodal Imitation
Jul 11, 2026He Zhang, Ying Sun, Ziyang Chen +6Multimodal Action Distributions Conditional Flow Matching
The Hong Kong University of Science and Technology (Guangzhou) · AI2 Robotics
MAG: A Web-Agent Benchmark and Harness for Multimodal Action and Guide Generation
Jul 11, 2026Chengguang Gan, Hanjun Wei, Yunhao Liang +3Web Agents Multimodal Agents
Independent Researcher · University of Chinese Academy of Sciences · Monash University +2
UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning
Jul 5, 2026Niu Lian, Alan Chen, Zhehao Yu +8Graphical User Interface Agents Multimodal Agents
Tsinghua Shenzhen International Graduate School, Tsinghua University · Harbin Institute of Technology, Shenzhen · Zhejiang University +2
XS-VLA: Teaching Tiny Vision-Language-Action Models with Spatial Supervision and Demonstration Conditioning
Jul 5, 2026Iok Tong Lei, Ying Jie Yap, Wei Huang +5Multimodal Action Distributions Spatial Grounding
Department of Computer Science and Technology, Tsinghua University, Beijing, China. · National College for Excellent Engineers, Beihang University, Beijing, China. · Independent Researcher +1
Worldscape-MoE: A Unified Mixture-of-Experts World Model for Scalable Heterogeneous Action Control
Jul 4, 2026Jianjie Fang, Yongyan Xu, Ziyou Wang +13Multimodal Action Distributions Action Space
Tsinghua University · Manifold AI
High-Fidelity One-Step Generative Visuomotor Policy via Recursive Correction, Frequency Consistency, and Contrastive Flow Matching
Jul 4, 2026Yuran Chen, Xinye Cai, Zhonglin Gong +1Visuomotor Policy Visuomotor Control
School of Safety Science and Engineering, Anhui University of Science and Technology, Huainan 232001, China · State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining, Anhui University of Science and Technology, Huainan 232001, China · School of Artificial Intelligence, Anhui University of Science and Technology, Hefei 231131, China
Dual-Flow Reinforcement Learning with State-Aware Exploration
Jun 29, 2026Qijun Li, Zheng Fu, Qi Song +4Multimodal Action Distributions Soft Actor-Critic
School of Vehicle and Mobility and the State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing 100084, China
FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning
Jun 23, 2026Xirui Li, Zhe Liu, Xiaoqing Ye +4Multimodal Action Distributions Distributions
1The University of Hong Kong · 2Changan Automobile
Flowing With Purpose: Latent Action Guided Flow Matching Policies For Robotic Manipulation
Jun 22, 2026Bruno Machado, Alexandre Chapin, Emmanuel Dellandrea +1Multimodal Action Distributions Robotic Manipulation
École Centrale de Lyon · LIRIS, UMR5205
CoRDE: Concept-Prior Routed Diffusion Experts for Structural Generalization in Robot Manipulation
Jun 20, 2026Haidong Huang, Xixin Zhao, Yaohua Zhou +5Diffusion Policies Multimodal Action Distributions
College of Information Science and Technology, Eastern Institute of Technology, Ningbo, Ningbo 315200, China · Faculty of Science and Engineering, University of Nottingham Ningbo China, Ningbo 315100, China · Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511453, China +2
VQActFlow: Vector-Quantized Action Mode Steering for Multi-Task Robot Manipulation
Jun 19, 2026Zhigen Zhao, Mark Leggiero, Yipu Chen +5Multimodal Action Distributions Robotic Manipulation Policies
Institute for Robotics and Intelligent Machines (IRIM), Georgia Institute of Technology, Atlanta, GA 30332
FlowMaps: Modeling Long-Term Multimodal Object Dynamics with Flow Matching
Jun 18, 2026Francesco Argenziano, Miguel Saavedra-Ruiz, Sacha Morin +3Flow Map Multimodal Action Distributions
Sapienza University of Rome, Rome, Italy · Universit´e de Montr´eal, Montr´eal, QC, Canada · Mila - Quebec AI Institute, Montr´eal, QC, Canada
Frequency-Aware Flow Matching for Continuous and Consistent Robotic Action Generation
Jun 18, 2026Jianing Guo, Fangzheng Chen, Zihao Mao +12Multimodal Action Distributions Conditional Flow Matching
Beihang University · PKU-Psibot Lab · The Chinese University of Hong Kong +3
One-to-Two Acting: A Novel Framework for Single-arm Agent Action Expansion to Dual Arms
Jun 18, 2026Youbin Yao, Nieqin Cao, Mingyan Li +3Bimanual Manipulation Multimodal Action Distributions
1Chongqing University, Chongqing, China · 2Xi’an Jiaotong-Liverpool University, Suzhou, China · 3Lumos Roboticss
FlowMPC: Improving Flow Matching policies with World Models
Jun 15, 2026Chandon HamelEfficient World-Action Model Multimodal Action Distributions
Stanford University
DRIVE: Distributional and Retrieval-Augmented Bidding with Value Evaluation
Jun 12, 2026Miduo Cui, Haochen Wang, Shangqin Mao +6Bidding Multimodal Action Distributions
Shandong University, Jinan, China · Meituan, Beijing, China
Guided Discovery of New Behaviors using Diffusion Policies
Jun 7, 2026Dian Yu, Sebastian Sanokowski, Majid KhadivDiffusion Policies Robot Policies
Munich Institute of Robotics and Machine Intelligence, Technical University of Munich
Flash-WAM: Modality-Aware Distillation for World Action Models
Jun 3, 2026Arman Akbari, Ci Zhang, Arash Akbari +6Multimodal Action Distributions
1Northeastern University · University of Georgia · 3EmbodyX Inc.
Denoising Tells When to Replan: Denoising-Variance Adaptive Chunking for Flow-Based Robot Policies
Jun 2, 2026Xiangdong Feng, Yuxuan Cheng, Chen Shi +5Action Chunks Iterative Re-Planning
Beijing Institute of Technology · Shenzhen Loop Area Institute · The Chinese University of Hong Kong, Shenzhen +4
Let the Dynamics Flow: Stable Flow Matching Dynamical Systems
Jun 2, 2026Rodrigo Pérez-Dattari, Francisco Leiva, Andrea Testa +3Imitation Learning Multimodal Action Distributions
Department of Robotics, Perception, and Learning, KTH Royal Institute of Technology, Stockholm, Sweden. · Advanced Mining Technology Center (AMTC) and Department of Electrical Engineering, Universidad de Chile, Santiago, Chile. · Bosch Center for Artificial Intelligence, Renningen, Germany. +1
Multimodal Action Diffusion for Robust End-to-End Autonomous Driving
Jun 1, 2026Jorge Daniel Rodríguez-Vidal, Diego Porres, Gabriel Villalonga Pineda +1Causality-Aware End-To-End Autonomous Driving Multimodal Action Distributions
Computer Vision Center (CVC) Barcelona, Spain · Universitat Autònoma de Barcelona (UAB) Barcelona, Spain
Learning Multi-Modal Trajectory Policies for Data-Efficient Robotic Manipulation
May 31, 2026Zijia Chen, Yuenan Hou, Xinhua Jiang +3Multimodal Action Distributions Robotic Manipulation
College of Electronic Science and Technology, National University of Defense Technology Changsha, 410073, China · Shanghai AI Laboratory Shanghai, 200000, China
Polyphony: Diffusion-based Dual-Hand Action Segmentation with Alternating Vision Transformer and Semantic Conditioning
May 29, 2026Hao Zheng, Hu Wang, Tiantian Zheng +2Temporal Action Segmentation Bimanual Manipulation
New York University Abu Dhabi, Abu Dhabi, United Arab Emirates · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates
MARS Policy: Multimodality Only When It Matters
May 28, 2026Jindou Jia, Tuo An, Yuxuan Hu +7Multimodal Action Distributions Imitation Learning
1MARS Lab, Nanyang Technological University
Adversarial Dual On-Policy Distillation from Expressive Teacher
May 26, 2026Zhenglin Wan, Jingxuan Wu, Xingrui Yu +5Multimodal Action Distributions Behavior Cloning
School of Computing, National University of Singapore · Department of Statistics and Operations Research, UNC-Chapel Hill, America · CFAR, Agency for Science, Technology and Research, Singapore +4
Smoother Action Chunking Flow Policy via Prior-Corrected Orthogonal Trust-Region Guidance
May 23, 2026Kai Fang, Hailong Pei, Xuemin ChiAction Chunks Flow Policies
South China University of Technology · Guangzhou, China · Zhejiang University +1
Understanding Multimodality in Generative Behavioral Cloning
May 21, 2026Lorenzo Mazza, Massimiliano Datres, Ariel Rodriguez +3Multimodal Action Distributions Behavior Cloning
NCT/UCC Dresden, UKDD Dresden, TU Dresden, DKFZ Heidelberg · Ludwig-Maximilians-Universität München, Munich Center for Machine Learning (MCML) · BMFTR Research Hub 6G-Life +4
RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation
May 17, 2026Sixu Lin, Junliang Chen, Huaiyuan Xu +8Robotic Manipulation Multimodal Action Distributions
School of Data Science, The Chinese University of Hong Kong (Shenzhen) · The Hong Kong Polytechnic University · Shenzhen Loop Area Institute +1
Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulation
May 12, 2026Junjin Xiao, Dongyang Li, Yandan Yang +9Diffusion-Based Vision-Language-Actions Robotic Manipulation
Shenzhen University of Advanced Technology
Behavioral Mode Discovery for Fine-tuning Multimodal Generative Policies
May 12, 2026Alberta Longhini, David Emukpere, Jean-Michel Renders +1Multimodal Action Distributions Reinforcement Fine-Tuning
Department of Computer Science, Stanford University, CA, USA
ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matching
May 11, 2026Shuoheng Zhang, Yifu Yuan, Hongyao Tang +7Force Multimodal Action Distributions
Tianjin University · Shanghai AI Lab · Huawei Noah’s Ark Lab
Parameter-Efficient Multi-View Proficiency Estimation: From Discriminative Classification to Generative Feedback
May 5, 2026Edoardo Bianchi, Antonio LiottaMulti-View Proficiency
Faculty of Engineering, Free University of Bozen-Bolzano, Bozen-Bolzano, Italy
MoE-ACT: Scaling Multi-Task Bimanual Manipulation with Sparse Task-Conditioned Mixture-of-Experts Transformers
Mar 16, 2026Kangjun Guo, Haichao Liu, Yanji Sun +3Bimanual Manipulation Robotic Manipulation
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511453, China · The Hong Kong University of Science and Technology, Hong Kong SAR, China
CoLA-Flow Policy: Temporally Coherent Imitation Learning via Continuous Latent Action Flow Matching for Robotic Manipulation
Jan 30, 2026Wu Songwei, Jiang Zhiduo, Sun Wandong +4Temporally Coherent Imitation Learning Flow Policies
Harbin Institute of Technology, Harbin 150001, China · Honor Device Co., Ltd., Shenzhen, China
Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos
Dec 1, 2025Xavier Thomas, Youngsun Lim, Ananya Srinivasan +2Human Motion Generation Human Motion
Boston University · Belmont High School · Canyon Crest Academy +1

Oct 1, 2026, cs.LGJ/K move · Enter open · S save

Flowing Faster to Coordinate: One-Step Online Multi-Agent Flow Policies

Zhuoran Li, Yunzhan Li, Xun Wang, Yihan Du+1

Institute for Interdisciplinary Information Sciences, Tsinghua University · Engineering Systems and Design Pillar, Singapore University of Technology and Design

Multi-Agent Reinforcement Learning Flow Policies Multimodal Action Distributions Flow Models

Open paper AskPDF arXiv

Multi-agent reinforcement learning (MARL) provides a powerful framework for learning coordinated behaviors through interactions with the environment. Developing MARL policies requires balancing expressive modeling of complex and multimodal action distributions with efficient training and execution. Generative policies, particularly diffusionbased policies, can faithfully capture complex and multimodal behaviors, but costly iterative sampling hinders their scalability in online multi-agent settings. We propose an Online MARL framework via one-step Flow model (OMAF) that combines expressive generative policies with efficient one-step action generation. OMAF employs a Transformer-based flow policy to capture complex coordination behaviors, while its approximate path score surrogate provides a principled route to synchronized flow policy optimization. To enable stable and sampleefficient learning, we further develop a joint optimization scheme coupling softmax Q-value estimation with a joint flow policy objective for coordinated policy learning. By eliminating iterative sampling, OMAF dramatically reduces training overhead without sacrificing policy expressiveness. Extensive experiments across 10 standard tasks from MPE and MAMuJoCo show that OMAF consistently achieves superior performance, with up to 3.4x higher returns and 10.5x sample efficiency improvement compared with baseline methods. These results validate the effectiveness of OMAF as an expressive and computationally efficient one-step flow policy paradigm for online MARL.

Momentum

Related topics

Latest papers 52