Generative Flow Networks

Also known as GFlowNet

Overview

Generative Flow Networks (GFlowNets) build objects through sequences of actions and learn to sample completed objects in proportion to their rewards, offering an alternative to finding only the single best solution. Common training methods include flow matching, detailed balance, and trajectory balance, with replay, policy-gradient updates, and learned action abstractions used to improve exploration and efficiency. Applications include molecule and crystal design, graph generation, language-model reasoning, and strategic decision-making. Current work seeks to scale these methods while preserving diversity and stable training, and to establish when training objectives reliably guarantee that the learned sampler matches the target reward distribution.

Latest papers

CardsList

64 papers7 papers in the last four weeks, down 36% on the four weeks before. 0.1% of all new papers.

  1. GFlowQEC: Generative Flow Networks that Learn to Sample Quantum LDPC Codes

    Nov 4, 2026Nuno Batista, Gabriel Falcao, Penousal MachadoQuantum Error CorrectionQuantum LDPC Codes

  2. Asynchronous Flow Map Language Models

    Oct 30, 2026Chanhyuk Lee, Wonjung Kim, Patrick Pynadath +5Language ModelingOne-Step Generative Modeling

  3. On the Generation Order in GFlowNets

    Oct 30, 2026Timofei Gritsaev, Evgeny Katasonov, Ildus Sadrtdinov +2Generative Flow NetworksAutoregressive Generation

  4. DEG: Diffusion-Enhanced GFlowNet for Solving Vehicle Routing Problems

    Oct 29, 2026Ni Zhang, Zhiqin Zhang, Ling Pan +2Neural Combinatorial OptimizationVehicle Routing

  5. Rethinking GFlowNet Training: Negative Reinforce Dynamics

    Oct 28, 2026Pedro Dall'Antonia, Daniel Csillag, Diego MesquitaGenerative Flow NetworksGradient Descent Dynamics

  6. Discovery of Diverse and Realistic Financial Tail-Risk Using Generative Flow Networks

    Oct 28, 2026Adir Serruya, Gilad KatzGenerative Flow NetworksDiversity-Aware Sampling

  7. Hierarchical Cooperative GFlowNets

    Oct 25, 2026Pedro Dall'Antonia, Juan Belieni, Ana Carolina Erthal +3Generative Flow NetworksDiversity-Aware Sampling

  8. Mixture of GFlowNets

    Oct 12, 2026Omar G. Younis, Joseph D. Viviano, Chirayu Anant Haryan +3Generative Flow NetworksMode Collapse

  9. Towards Understanding the Training of GFlowNets: A Theoretical Perspective

    Oct 9, 2026Rui Hu, Yu Chen, Zhuoran Li +1Generative Flow NetworksFlow Matching

  10. Learning a Mixture of GFlowNets

    Oct 6, 2026Tiago da Silva, Amauri H. Souza, Salem LahlouGenerative Flow Networks

  11. Universality and Convergence of Generative Flows

    Oct 4, 2026Leo BrunswicFlow MatchingGenerative Flow Networks

  12. Beyond Mode Collapse: Generating Diverse Synthetic Expert Conversations via Generative Flow Networks

    Sep 29, 2026Sumit Asthana, Michael Ion, Kevyn Collins ThompsonGenerative Flow NetworksFlow-Based Generative Modeling

  13. One Proposal for Every Margin: Zero-Shot Amortized Sequential Importance Sampling for Binary Matrices

    Sep 28, 2026Ruishuo Chen, Weijia Li, Xun Wang +3Importance SamplingGenerative Flow Networks

  14. 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 +6Generative Flow NetworksMulti-Teacher Knowledge Distillation

  15. R2^2 Flow: Recursive Self-Improvement via Recursive Skill Evolution

    Sep 27, 2026Mingda Zhang, Qiang Huang, Yanjin Li +4LLM Agent Self-ImprovementGenerative Flow Networks

  16. WTF?! Simulation-Free Reinforcement Learning with Wasserstein-Tilted Flow Maps

    Sep 22, 2026Abbas Mammadov, Jerry Y. Huang, Justin Lin +5Simulation-Based RLReinforcement Learning

  17. Particle GFlowNets: Rethinking Generative Marginalization Models

    Sep 10, 2026Tiago da Silva, Diego Mesquita, Salem LahlouMarkov Chain Monte CarloGenerative Flow Networks

  18. FlowNeg: GFlowNet-Guided Diverse Hard Negative Sampling for Knowledge Graph Embedding

    Aug 24, 2026Ibne Farabi Shihab, Naoshin Anzum Hridi, Joyanta Jyoti MondalKG EmbeddingHard Negative Mining

  19. CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction

    Aug 6, 2026Kaixiang Su, Hongfei Xue, Qiang ZhuCrystal Structure PredictionGroup Relative Policy Optimization

  20. IFlowNets: Extending Generative Samplers to Learn Strategies in Incomplete Information Games

    Aug 5, 2026Conor M. Artman, Nicholas Di, Scott PerkinsImperfect-Information GamesGenerative Flow Networks

  21. Information-Geometric Forward Policy Training in GFlowNets

    Aug 4, 2026Yordan Raykov, Rodrigo VeigaInformation GeometryNatural Gradient Methods

  22. GFlowRL: Scaling Distribution-Matching RL to Large Language Models

    Jul 15, 2026Xiaodong Liu, Michael Xu, Jack W. Stokes +3RL for Code GenerationReinforcement Learning

  23. Self-conditioned Flow Map Language Models via Fixed-point Flows

    Jul 1, 2026Jaehoon Yoo, Wonjung Kim, Floor Eijkelboom +4Normalizing FlowsOne-Step Generative Modeling

  24. Posterior Refinement: Fast Language Generation via Any-Order Flow Maps

    Jun 23, 2026Manan Agarwal, Sheel Shah, Chanhyuk Lee +6Non-Autoregressive Text GenerationGenerative Flow Networks

  25. FlowPipe: LLM-Enhanced Conditional Generative Flow Networks for Data Preparation Pipeline Construction

    Jun 23, 2026Kunyu Ni, Lei Cao, Jie He +4Generative Flow NetworksFlow-Based Generative Modeling

  26. Latent Thought Flow: Efficient Latent Reasoning in Large Language Models

    Jun 15, 2026Xiandong Zou, Jing Huang, Jianshu Li +1RL for Language Model ReasoningEfficient Language Model Reasoning

  27. Proximal Policy Optimization for Amortized Discrete Sampling

    Jun 14, 2026Anna Zykova-Myzina, Timofei Gritsaev, Daniil Tiapkin +1Molecular Graph GenerationGenerative Flow Networks