Flow Models

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 39

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
Multimodal Flow: Unified Flow Modeling of Language and Vision in Embedding Spaces
Sep 30, 2026Hongyuan Tao, Xinggang Wang, Lianghui Zhu +7Multimodal Pretraining Multimodal Representations
Huazhong University of Science and Technology · Beijing Jiaotong University · Horizon Robotics
CapField-OPD: Learning Continuous Capability Fields via Joint-Anchored Multi-Teacher On-Policy Distillation for Flow Models
Sep 28, 2026Pengyang Ling, Jiazi Bu, Yujie Zhou +6Aware Heterogeneous Multi-Teacher Multimodal On-Policy Distillation Generative Flow Networks
University of Science and Technology of China · Shanghai Jiao Tong University · Fudan University +2
Elucidating the Design Space of Regression-based Diffusion Reinforcement Learning
Sep 27, 2026Toyota Li, David Zhao, Alan ZhaoDiffusion-Based Reinforcement Learning Methods Reward Gradients
Tencent
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
FlowCPO: A Unified Divergence View of Preference Alignment for Flow Models
Sep 9, 2026Yansen Han, Shengyi Liao, Peng Sun +4Flow Models Preference Alignment
Westlake University · Zhejiang University · Kling Team, Kuaishou Technology
Multiple Hypothesis Flow Estimation for Video Frame Interpolation under Matching Ambiguity
Aug 7, 2026Zibo Su, Jing Kong, Ruixing Wang +2Optical Flow Video Restoration
1Xidian University · 2DJI Technology Co., Ltd.
Poly-OPD: Heterogeneous Multi-Teacher On-Policy Distillation for Capability-Selectable Flow Models
Aug 5, 2026Siming Fu, Haojun Xu, Ruizhe He +9Aware Heterogeneous Multi-Teacher Multimodal On-Policy Distillation Uni-Opd
1Joy Future Academy · 2Zhejiang University · 3Beihang University
Flow Map Learning via Nongradient Vector Flow
Jul 29, 2026Mark Goldstein, Anshuk Uppal, Raghav Singhal +2Flow Map Invertible Flows
Center for Computational Mathematics, Flatiron Institute. · Department of Applied Mathematics and Computer Science, Technical University of Denmark. · Courant Institute, New York University.
FlowCTS: On-policy Continuous Trajectory Supervision of Flow Models
Jul 27, 2026Kaiyang Ye, Yuan Ge, Junxiang Zhang +8Flow Models Token-Level Supervision
Northeastern University · NiuTrans Research · Kunming University of Science and Technology
Stability of Flow Models for Graph Signals
Jul 8, 2026Martin Schmidt, Gonzalo MateosGenerative Flow Networks Flow Models
Dept. of Electrical and Computer Engineering, University of Rochester, Rochester, NY 14627, USA
OpFlow: Learning Opportunity-Conditioned Choice Potentials for Robust OD Flow Prediction
Jul 3, 2026Changjian Liu, Yong Gao, Yuqing Wang +5Origin Destination Flows Flow Models
School of Earth and Space Sciences Peking University China, CN 100871 · College of Artificial Intelligence Zhejiang University China, CN 310027
PedNStream: Scalable Network Flow Simulation for Pedestrian Traffic Management
Jul 1, 2026Weiming Mai, Dorine Duives, Serge HoogendoornMicroscopic Traffic Simulations Flow Models
Department of Transportation and Planning, Delft University of Technology, Delft, Netherlands
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 +2Robotic Manipulation Action Generation
Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China · Institute for Artificial Intelligence, Tsinghua University, Beijing 100084, China
An Optimal Contact-Mechanically Consistent and Flow-Separation Adapted Modeling of Vocal Fold Dynamics
Jun 27, 2026Sardar Nafis Bin Ali, Maryam Naghibolhosseini, Mohsen ZayernouriVocal Tract Shape Vocalizations
Department of Mechanical Engineering, Michigan State University, 428 S. Shaw Lane, East Lansing, 48824, MI, USA. · Department of Communicative Sciences and Disorders, Michigan State University, 1026 Red Cedar Rd, East Lansing, 48824, MI, USA.
Physics-Grounded Disentangled Flow Modeling for Brain Disease Progression Trajectory
Jun 26, 2026Jun Wang, Peirong LiuLongitudinal Imaging Disease
Department of Electrical and Computer Engineering, Data Science and AI Institute, Johns Hopkins University
Don't Settle at the Mode! Mitigating Diversity Collapse in Pretrained Flow Models via Feature Self-Guidance
Jun 25, 2026Pradhaan S Bhat, Rishubh Parihar, Abhijnya Bhat +1Generative Flow Networks Diversity Collapse
Indian Institute of Science · Stanford University
DynaOD: Dynamic Origin-Destination Flow Generation with Discrete-to-Continuous Temporal Semantic Modeling
Jun 8, 2026Jie Zhao, Xianqi Dai, Jie Feng +2Origin Destination Flows Temporal Dynamics
Department of Electronic Engineering, BNRist, Tsinghua University · Tsinghua Shenzhen International Graduate School · Zhongguancun Academy
Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules
Jun 7, 2026Riccardo De Santi, Bruce Lee, Cristian Perez Jensen +6Generative Flow Networks Flow Models
ETH Zurich ETH AI Center · University of Pennsylvania · Caltech FutureHouse
AdvantageFlow: Regularized Advantage-Weighted RL in Flow Models
May 25, 2026Branislav Kveton, Anup Rao, Subhojyoti Mukherjee +2Flow Models Rectified Flow
Adobe Research
VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimation
May 22, 2026Junwen Tan, Jinglin Liang, Hongyuan Chen +1Rectified Flow Conditional Velocity
South China University of Technology
Conflict-Aware Additive Guidance for Flow Models under Compositional Rewards
May 20, 2026Xuehui Yu, Fucheng Cai, Meiyi Wang +2Flow Models Geometric Guidance
Smart Systems Institute, National University of Singapore, Singapore · Faculty of Computing, Harbin Institute of Technology, Harbin, China · School of Computing, National University of Singapore, Singapore
A Unified Framework for Structured Flow Modeling: From Representation to Verification and Model Discovery
May 18, 2026Diego CasadeiVector Fields Flow Models
Fly High Engineering AG, Badenerstrasse 13, 5200 Brugg AG, Switzerland
Human-Flow Digital Twin for Predicting the Effects of Mobility Introduction on Visitor Circulation
May 17, 2026Chiharu Shima, Haruki Yonekura, Fukuharu Tanaka +2Mobility Cognitive Digital Twins
bitA Inc., Shinagawa-ku, Tokyo, Japan · The University of Osaka, Suita, Osaka, Japan · RIKEN Center for Computational Science, Kobe, Hyogo, Japan
Embedding-perturbed Exploration Preference Optimization for Flow Models
May 15, 2026Sujie Hu, Chubin Chen, Jiashu Zhu +3Stochastic Exploration Flow Models
1Tsinghua University · ⋆Work done during the internship at AMAP · 2AMAP, Alibaba Group
Asymmetric Flow Models
May 13, 2026Hansheng Chen, Jan Ackermann, Minseo Kim +2Latent Flow Flow Models
Stanford University
dFlowGRPO: Rate-Aware Policy Optimization for Discrete Flow Models
May 10, 2026Zhengyan Wan, Yidong Ouyang, Panwen Hu +1Flow Models Diffusion-Based Reinforcement Learning Methods
Mohamed bin Zayed University of Artificial Intelligence · East China Normal University · University of California, Los Angeles +1
Restoration-Aligned Generative Flow Models for Blind Motion Deblurring
May 9, 2026Insoo Kim, Jinwoo ShinGaussian Deblurring Flow Models
1NAVER Cloud · 2KAIST AI
FlowADMM: Plug-and-play ADMM with Flow-based Renoise-Denoise Priors
May 9, 2026Hendrik Sommerhoff, Michael MoellerBayesian Inverse Problems Iterative Denoising Methods
Computer Vision Group, University of Siegen Hölderlinstraße 3, 57076 Siegen, Germany
Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field
May 8, 2026Kim Yong Tan, Yueming Lyu, Ivor Tsang +1Generative Flow Networks Flow Models
College of Computing and Data Science, Nanyang Technological University, Singapore · Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore · Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore
Improved techniques for fine-tuning flow models via adjoint matching: a deterministic control pipeline
May 7, 2026Zhengyi Guo, Jiayuan Sheng, David D. Yao +1Flow Models Generative Flow Networks
RepFlow: Representation Enhanced Flow Matching for Causal Effect Estimation
May 7, 2026Yifei Xie, Jian HuangCausal Inferences Selection Bias
Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong, China.
A Few-Step Generative Model on Cumulative Flow Maps
May 5, 2026Zhiqi Li, Duowen Chen, Yuchen Sun +1Flow Map Flow Models
Georgia Institute of Technology, Atlanta, United States of America
A unified perspective on fine-tuning and sampling with diffusion and flow models
Apr 30, 2026Carles Domingo-Enrich, Yuanqi Du, Michael S. AlbergoGenerative Flow Networks Adjoint Matching
Microsoft Research New England · Harvard University, Kempner Institute
Neuro-Symbolic ODE Discovery with Latent Grammar Flow
Apr 17, 2026Karin Yu, Eleni Chatzi, Georgios KissasNeuro-Symbolic Framework Latent Flow
Institute of Structural Engineering, ETH Zurich, Zurich, Switzerland · ETH AI Center, ETH Zurich, Zurich, Switzerland · Swiss Data Science Center, Zurich, Switzerland
Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models
Mar 15, 2026Niklas Schweiger, Daniel Cremers, Karnik RamDiffusion Alignment Generative Flow Networks
Technical University of Munich, Germany · Munich Center for Machine Learning, Germany
Momentum Guidance: Plug-and-Play Guidance for Flow Models
Feb 23, 2026Runlong Liao, Jian Yu, Baiyu Su +3Flow Models Classifier-Free Guidance
The University of Texas at Austin, Austin, TX 78712, USA
Native Extrapolation Awareness in Flow-Based Conditional Generation
Feb 13, 2026Constantinos Tsakonas, Serena Ivaldi, Jean-Baptiste MouretFlow Models Extrapolation
Inria, Université de Lorraine, CNRS, Loria Nancy, France
Trajectory Stitching for Solving Inverse Problems with Flow-Based Models
Feb 9, 2026Alexander Denker, Zeljko Kereta, Carola-Bibiane Schönlieb +1Flow Models Inverse Problem
Department of Computer Science, University College London · Department of Applied Mathematics and Theoretical Physics, University of Cambridge.

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 39