Generative Flow Networks

Also known as GFlowNet

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, with none the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 40

All topics

CoFlow: Coordinated Few-Step Flow for Offline Multi-Agent Decision Making
May 2, 2026Guowei Zou, Haitao Wang, Beiwen Zhang +2Flow Matching Multi-Agent Coordination
Sun Yat-sen University
Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance
May 1, 2026Minchan Kwon, Sunghyun Baek, Minseo Kim +3Language Model Safety Evaluation Adversarial Attacks on LLMs
1KAIST · 2Naver AI Lab.
GFlowState: Visualizing the Training of Generative Flow Networks Beyond the Reward
Apr 23, 2026Florian Holeczek, Andreas Hinterreiter, Alex Hernandez-Garcia +2Data Visualization Generative Flow Networks
Johannes Kepler University Linz · Mila – Quebec AI Institute · Eidgenössische Technische Hochschule Zürich
Trajectory Stitching for Solving Inverse Problems with Flow-Based Models
Feb 9, 2026Alexander Denker, Zeljko Kereta, Carola-Bibiane Schönlieb +1Generative Flow Networks Flow-Based Generative Modeling
Department of Computer Science, University College London · Department of Applied Mathematics and Theoretical Physics, University of Cambridge.
Why Pool When You Can Flow? Active Learning with GFlowNets
Aug 31, 2025Renfei Zhang, Mohit Pandey, Artem Cherkasov +1Active Learning Virtual Screening
School of Computer Science, Simon Fraser University, Burnaby, BC, Canada · Vancouver Prostate Centre, University of British Columbia, Vancouver, BC, Canada · Diagen AI +1
Action abstractions for amortized sampling
Oct 19, 2024Oussama Boussif, Léna Néhale Ezzine, Joseph D Viviano +6Hierarchical RL Generative Flow Networks
Mila – Qu´ebec AI Institute · Universit´e de Montr´eal · University of Toronto +3
Amortizing intractable inference in large language models
Oct 6, 2023Edward J. Hu, Moksh Jain, Eric Elmoznino +4Amortized Inference LLM Fine-Tuning
Mila – Quebec AI Institute, Universit´e de Montr´eal · University of Oxford
Expected flow networks in stochastic environments and two-player zero-sum games
Oct 4, 2023Marco Jiralerspong, Bilun Sun, Danilo Vucetic +4Game-Playing Agents Zero-Sum Games
Mila – Qu´ebec AI Institute, Universit´e de Montr´eal
GFlowNets and variational inference
Oct 2, 2022Esmeralda S. Whitammer, Salem Lahlou, Tristan Deleu +5Generative Flow Networks RL for Generative Models
Mila, Universit´e de Montr´eal · Google Research · Mila, Universit´e de Montr´eal, CIFAR
Partial GFlowNet: Accelerating Convergence in Large State Spaces via Strategic Partitioning
Date pendingXuan Yu, Xu Wang, Rui Zhu +2Reinforcement Learning Generative Flow Networks
University of Science and Technology of China (USTC), Hefei, China · Suzhou Institute for Advanced Research, USTC, Suzhou, China · State Key Laboratory of Precision and Intelligent Chemistry, USTC, Hefei, China

May 2, 2026, cs.AIJ/K move · Enter open · S save

CoFlow: Coordinated Few-Step Flow for Offline Multi-Agent Decision Making

Guowei Zou, Haitao Wang, Beiwen Zhang, Boning Zhang+1

Sun Yat-sen University

Flow Matching Multi-Agent Coordination Generative Flow Networks Flow-Based Generative Modeling Multi-Agent Reinforcement Learning Offline MARL

Open paper AskPDF arXiv

Generative models have emerged as a promising paradigm for offline multi-agent reinforcement learning (MARL), but existing approaches require many iterative sampling steps. Recent few-step acceleration methods either distill a joint teacher into independent students or apply averaged velocity fields independently to each agent. Unfortunately, these few-step approaches hurt inter-agent coordination. We show that the efficiency-coordination trade-off is not inherent: single-pass multi-agent generation can preserve coordination when the velocity field is natively joint-coupled. We propose Coordinated few-step Flow (CoFlow), an architecture that combines Coordinated Velocity Attention (CVA) with Adaptive Coordination Gating. A finite-difference consistency surrogate further replaces memory-prohibitive Jacobian-vector product backpropagation through the averaged velocity field with two stop-gradient forward passes. Across 60 configurations spanning MPE, MA-MuJoCo, and SMAC, CoFlow matches or surpasses Gaussian policies, value-based methods, transformer policies, diffusion models, and prior flow baselines on episodic return. Three independent coordination probes confirm that CoFlow's improvements arise from inter-agent coordination rather than per-agent capacity. A denoising-step sweep shows that single-pass inference suffices on every configuration. CoFlow reaches state-of-the-art coordination quality in 1-3 denoising steps under both centralized and decentralized execution. Project Page: https://guowei-zou.github.io/coflow/

Momentum

Related topics

Latest papers 40