mlsanityData to 7 Oct 2026

GFlowNet Foundations

arXiv 2111.09266 ↗First posted 17 Nov 2021cs.LG cs.AI stat.MLcited by 286

Not on the map. Why?

Cited by 35 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Generative Flow Networks (GFlowNets) have been introduced as a method to sample a diverse set of candidates in an active learning context, with a training objective that makes them approximately sample in proportion to a given reward function. In this paper, we show a number of additional theoretical properties of GFlowNets. They can be used to estimate joint probability distributions and the corresponding marginal distributions where some variables are unspecified and, of particular interest, can represent distributions over composite objects like sets and graphs. GFlowNets amortize the work typically done by computationally expensive MCMC methods in a single but trained generative pass. They could also be used to estimate partition functions and free energies, conditional probabilities of supersets (supergraphs) given a subset (subgraph), as well as marginal distributions over all supersets (supergraphs) of a given set (graph). We introduce variations enabling the estimation of entropy and mutual information, sampling from a Pareto frontier, connections to reward-maximizing policies, and extensions to stochastic environments, continuous actions and modular energy functions.

Key facts. Cited by 286 papers in the map (data through 7 Oct 2026). Builds on 29 of its 72 references that are in the map. First posted on arXiv 17 Nov 2021.

Builds on

29 of 72 references.

References · 29

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  4. 2015Variational Inference with Normalizing Flowscited by 2,161
  5. 2016Density estimation using Real NVPcited by 2,029
  6. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  7. 2017A Distributional Perspective on Reinforcement Learningcited by 743
  8. 2017Reinforcement Learning with Deep Energy-Based Policiescited by 659
  9. 2019Deep Equilibrium Modelscited by 603
  10. 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 555
  11. 2018Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Reviewcited by 466
  12. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 384
17 more
  1. 2017Grammar Variational Autoencodercited by 283
  2. 2020Inductive Biases for Deep Learning of Higher-Level Cognitioncited by 273
  3. 2019DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Correctionscited by 254
  4. 2019Recurrent Independent Mechanismscited by 219
  5. 2017Bridging the Gap Between Value and Policy Based Reinforcement Learningcited by 178
  6. 2021MARS: Markov Molecular Sampling for Multi-objective Drug Discoverycited by 125
  7. 2019Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actionscited by 124
  8. 2021Oops I Took A Gradient: Scalable Sampling for Discrete Distributionscited by 92
  9. 2019Elements of Sequential Monte Carlocited by 60
  10. 2019Maximum Entropy Generators for Energy-Based Modelscited by 55
  11. 2018Learning Actionable Representations with Goal-Conditioned Policiescited by 53
  12. 2020Learning Discrete Energy-based Models via Auxiliary-variable Local Explorationcited by 29
  13. 2019Autoregressive Energy Machinescited by 23
  14. 2018A Framework for Adaptive MCMC Targeting Multimodal Distributionscited by 21
  15. 2017Constrained Bayesian Optimization for Automatic Chemical Designcited by 20
  16. 2020Batch Stationary Distribution Estimationcited by 19
  17. 2019Discrete Object Generation with Reversible Inductive Constructioncited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 22; 2023: 55; 2024: 79; 2025: 74; 2026: 56.

286 papers.

Sort:

By area:

  1. 2024Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Designcited by 294
  2. 2022Trajectory balance: Improved credit assignment in GFlowNetscited by 244
  3. 2022Bayesian Structure Learning with Generative Flow Networkscited by 153
  4. 2024Fine-Tuning of Continuous-Time Diffusion Models as Entropy-Regularized Controlcited by 136
  5. 2022Learning GFlowNets from partial episodes for improved convergence and stabilitycited by 129
  6. 2022Generative Flow Networks for Discrete Probabilistic Modelingcited by 113
  7. 2022GFlowNets and variational inferencecited by 103
  8. 2023A theory of continuous generative flow networkscited by 98
  9. 2023Amortizing intractable inference in large language modelscited by 94
  10. 2024Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Reviewcited by 92
  11. 2023Better Training of GFlowNets with Local Credit and Incomplete Trajectoriescited by 83
  12. 2025Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matchingcited by 78
38 more
  1. 2023Towards Understanding and Improving GFlowNet Trainingcited by 74
  2. 2024Amortizing intractable inference in diffusion models for vision, language, and controlcited by 70
  3. 2022Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matchingcited by 67
  4. 2022Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidancecited by 67
  5. 2022MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Designcited by 66
  6. 2023GFlowNets for AI-Driven Scientific Discoverycited by 63
  7. 2023Generative Flow Networks as Entropy-Regularized RLcited by 60
  8. 2022DiffBP: Generative Diffusion of 3D Molecules for Target Protein Bindingcited by 58
  9. 2024A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimizationcited by 58
  10. 2023Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimizationcited by 57
  11. 2024Learning diverse attacks on large language models for robust red-teaming and safety tuningcited by 54
  12. 2024Ant Colony Sampling with GFlowNets for Combinatorial Optimizationcited by 53
  13. 2023Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Networkcited by 50
  14. 2022Generative Augmented Flow Networkscited by 48
  15. 2023Sample-efficient Multi-objective Molecular Optimization with GFlowNetscited by 48
  16. 2024Improved off-policy training of diffusion samplerscited by 47
  17. 2022Reinforced Genetic Algorithm for Structure-based Drug Designcited by 46
  18. 2023Local Search GFlowNetscited by 45
  19. 2023GFlowNet-EM for learning compositional latent variable modelscited by 40
  20. 2023Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNetscited by 40
  21. 2024Discrete Probabilistic Inference as Control in Multi-path Environmentscited by 40
  22. 2022A Variational Perspective on Generative Flow Networkscited by 39
  23. 2024RGFN: Synthesizable Molecular Generation Using GFlowNetscited by 39
  24. 2025FlowRL: Matching Reward Distributions for LLM Reasoningcited by 38
  25. 2024Genetic-guided GFlowNets for Sample Efficient Molecular Optimizationcited by 36
  26. 2023BayesDAG: Gradient-Based Posterior Inference for Causal Discoverycited by 33
  27. 2023Stochastic Generative Flow Networkscited by 32
  28. 2023Thompson sampling for improved exploration in GFlowNetscited by 31
  29. 2023Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaborationcited by 30
  30. 2023Maximum entropy GFlowNets with soft Q-learningcited by 30
  31. 2024Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNetscited by 30
  32. 2023Distributional GFlowNets with Quantile Flowscited by 28
  33. 2023A Survey on Explainability of Graph Neural Networkscited by 28
  34. 2024Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Predictioncited by 28
  35. 2025Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physicscited by 28
  36. 2023DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNetscited by 27
  37. 2024Improving GFlowNets for Text-to-Image Diffusion Alignmentcited by 27
  38. 2025Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Trainingcited by 27

50 most cited of 286 All 286 (JSON)