Discrete Flow Matching

Ask about this topic

Overview

Discrete flow matching models how a simple distribution over categories can be transformed into data such as text, graphs, or molecular sequences, offering a way to generate structured outputs through iterative refinement. Common approaches define continuous-time Markov chains and learn transition rates, using choices of coupling, noise schedule, and sampling order to shape the path; newer methods also add guidance, constraints, or distillation for faster generation. Applications include language and speech generation, molecule and biological sequence design, graph generation, and robot action prediction, often evaluated on standard task benchmarks and measures of validity, quality, and diversity. Work now spans scalable language models and practical domain-specific systems, while key challenges include reliable few-step sampling, handling constraints and variable-length structures, and understanding how training and source-distribution choices affect convergence and quality.

Latest papers

CardsList

34 papers6 papers in the last four weeks, up 50% on the four weeks before. 0.0% of all new papers.

  1. H-GLow: Accelerating Graph Generation via Hazard-Guided Discrete Flow Matching

    Oct 24, 2026Sirine Ayadi, Stephan GünnemannGraph GenerationDiscrete Flow Matching

    School of Computation, Information and Technology, Technical University of Munich · Munich Data Science Institute & Munich Center for Machine Learning

  2. Trajectory Matching: Discrete Flow Matching with Structured Actions

    Oct 23, 2026Niklas Kemper, Marten Lienen, David Lüdke +1Discrete Flow MatchingStructured Output Generation

    School of Computation, Information and Technology & Munich Data Science Institute, Technical University of Munich

  3. When Do Discrete Actions Make Good Continuous Controllers?

    Oct 14, 2026Zeji Yi, Soham Dasgupta, Xinyang Zhang +5Robot Policy LearningVLMs for Robotics

    Carnegie Mellon University · Amazon FAR (Frontier AI & Robotics)

  4. MIRRA: Fast, High-Fidelity Molecular Generation with Chemistry-Informed Discrete Flow Matching

    Oct 12, 2026Ge Sun, Juan J. de PabloMolecular GenerationMolecular Graph Generation

    Courant Institute of Mathematical Sciences, New York University, New York, NY 10012 · Tandon School of Engineering, New York University, Brooklyn, NY 11201 · Department of Physics, New York University, New York, NY 10003

  5. pCoMole: Pareto-Constrained Molecule Editing with Discrete Flows

    Oct 1, 2026Tong Chen, Maximilian Holsman, Lin Zhao +1Constrained Generative ModelingProtein Design

    Department of Computer and Information Science, University of Pennsylvania · Department of Computer Science, Duke University · Department of Bioengineering, University of Pennsylvania

  6. Zero Flux: Flow-Based Comparison of High-Dimensional Discrete Distributions

    Oct 1, 2026Leyang Wang, Yakun Wang, Song Liu +1Distribution ShiftDistribution Shift Detection

    Department of Mathematical Informatics, The University of Tokyo, Japan · Center for Advanced Intelligence Project, RIKEN, Japan · School of Mathematics, University of Bristol, United Kingdom

  7. Flow-Matching-Based Protein Structure Tokenizer Made Efficient and Easy

    Sep 27, 2026Zhe Zhang, Yikai Zhang, Jiangtao Feng +3Protein Representation LearningDiscrete Flow Matching

    Institute for AI Industry Research (AIR), Tsinghua University · Department of Computer Science and Technology, Tsinghua University · Fudan University

  8. Feasible Flow Matching for Graph Reconstruction via Within-Sampling Primal-Dual Guidance

    Sep 26, 2026Haoming Chen, Nicolas Zilberstein, Santiago Paternain +1Graph ReconstructionConstrained Generative Modeling

  9. Entropy Can Flow, or It Can Guide. Be Entropy. LEDFlow: Introducing Entropy-guided Generation Order into Uniform Discrete Flow

    Sep 20, 2026Tung Sum Thomas Kwok, Yidong Ouyang, Yingjia Wan +3Flow-Based Generative ModelingDiscrete Flow Matching

    University of California, Los Angeles · Shanghai Jiao Tong University

  10. Flow Duality and Source Geometry for Categorical Generation

    Sep 9, 2026Etrit HaxholliFlow MatchingFlow-Based Generative Modeling

  11. Mechanistic Reaction Prediction via Discrete Flow Matching on Graph-Structured Electron Occupation

    Aug 27, 2026Nguyen Xuan-Vu, Octavian Susanu, Daniel Armstrong +1Chemical Reaction PredictionDiscrete Flow Matching

    École Polytechnique Fédérale de Lausanne (EPFL) · National Centre of Competence in Research (NCCR) Catalysis

  12. Latent-Kernel Discrete Flow Maps for Few-Step Generation

    Jul 29, 2026Mansoor Ahmed, Yue-Tsz Fan, Hemanth Venkateswara +1Latent Variable ModelsFew-Step Diffusion Sampling

    Georgia State University, Atlanta, GA, USA · Georgia Institute of Technology, Atlanta, GA, USA

  13. Context-weighted Discrete Flow Matching

    Jul 23, 2026Daniil Cherniavskii, Daniel Severo, Karen UllrichNon-Autoregressive Text GenerationAdaptive Loss Weighting

    University of Amsterdam · Work done during an internship at Meta FAIR. · Meta FAIR

  14. LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flow

    Jul 12, 2026Hang Long, Tianhao Zhao, Junkai Lin +7Flow Matching3D Mesh Generation

    Huazhong University of Science and Technology · Meshy AI · Independent Researcher +1

  15. Flexible Inverse Design of Optical Multilayer Coatings Using Discrete-Continuous Flow Matching

    Jul 9, 2026Zhiyi Li, Yuheng Jin, Yidan Huang +3Flow MatchingInverse Design

    School of Electronic Science and Engineering (National Model Microelectronics College), Xiamen University, Fujian, 361005, China. · Fujian Key Laboratory of Ultrafast Laser Technology and Applications, Xiamen University, Xiamen, 361005, China.

  16. Flow Reasoning Models: Turning Flows Into Efficient Recurrent Reasoners

    Jun 28, 2026Alec Helbling, Andrey Bryutkin, Mauro Martino +3Self-ConditioningStructured Reasoning

    1Georgia Tech · 3MIT-IBM Computing Research Lab · 4IBM Research +1

  17. A Time-Reparameterized Cumulative Intensity Extrapolation Sampler for Discrete Flow Matching

    Jun 23, 2026Feiyang Fu, Hehe FanFlow MatchingFew-Step Diffusion Sampling

    College of Artificial Intelligence, Zhejiang University, Hangzhou, China.

  18. Flow6D: Discrete-to-Continuous Flow Matching for Efficient and Accurate Category-Level 6D Pose Estimation

    Jun 22, 2026Mingyu Mei, Li Zhang, Zibo Dai +4Flow MatchingObject Pose Estimation

    Zhejiang University · University of Science and Technology of China · Shanghai Jiao Tong University

  19. Mask, Sample, Revise: A Revisable CTMC Inference Stack for Guided Discrete Flow Matching Text-to-Speech

    Jun 12, 2026Alef Iury Siqueira Ferreira, Lucas Rafael Stefanel Gris, Luiz Fernando de Araújo Vidal +4Flow MatchingTTS Synthesis

    Federal University of Goi´as, Goiˆania, Brazil · Federal University of Mato Grosso, Cuiab´a, Brazil · Elsa Speak, S˜ao Paulo, Brazil

  20. Flexible Flows for Biological Sequence Design

    Jun 9, 2026Yogesh Verma, Dani Korpela, Harri Lähdesmäki +1Flow MatchingMolecular Generation

    Aalto University, Finland · Aalto University and YaiYai Ltd

  21. Discrete Flow Matching for Offline-to-Online Reinforcement Learning

    May 12, 2026Fairoz Nower Khan, Nabuat Zaman Nahim, Peizhong JuFlow MatchingReinforcement Learning

    Department of Computer Science, University of Kentucky

  22. Kinetic-Optimal Scheduling with Moment Correction for Metric-Induced Discrete Flow Matching in Zero-Shot Text-to-Speech

    May 10, 2026Dong Yang, Yiyi Cai, Haoyu Zhang +2Flow MatchingTTS Synthesis

    1The University of Tokyo · 2Independent Researcher

  23. Discrete Flow Matching: Convergence Guarantees Under Minimal Assumptions

    May 9, 2026Le-Tuyet-Nhi Pham, Giovanni Conforti, Zhenjie Ren +1Flow MatchingGenerative Modeling

    École Polytechnique, CMAP, IP Paris Route de Saclay, 91120 Palaiseau, France · Università degli Studi di Padova, Via Trieste, 63, 35131 Padova, Italia · LaMME, Université Évry Paris-Saclay Boulevard François Mitterrand 91000, France

  24. Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation

    May 8, 2026Amin Karimi Monsefi, Dominic Culver, Nikhil Bhendawade +3Flow MatchingDiffusion Language Model Inference

    1The Ohio State University · 2Apple

  25. Scaling Categorical Flow Maps

    May 8, 2026Oscar Davis, Anastasiia Filippova, Pierre Ablin +4Language Model ScalingFlow Map Learning

    Apple · University of Oxford

  26. Tree-Conditioned Edit Flows for Ancestral Sequence Reconstruction

    May 5, 2026Emil Sharafutdinov, Ingemar AndréFlow MatchingPhylogenetic Inference

    Center for Molecular Protein Science Lund University Box 124, 221 00 Lund

  27. Binomial flows: Denoising and flow matching for discrete ordinal data

    May 1, 2026Yair Shenfeld, Ricardo Baptista, Stefano PeluchettiFlow MatchingFlow-Based Generative Modeling

  28. Equivariant Efficient Joint Discrete and Continuous MeanFlow for Molecular Graph Generation

    Apr 9, 2026Rongjian Xu, Teng Pang, Zhiqiang Dong +1Molecular Graph GenerationGenerative Modeling

    School of Software, Shandong University, Jinan, Shandong, China · School of Software, Shandong University, Jinan, Shandong, China; Luke EI, Jinan, China

  29. Discrete Flow Matching Policy Optimization

    Apr 7, 2026Maojiang Su, Po-Chung Hsieh, Weimin Wu +4TV RegularizationRL for Flow Matching Models

    Center for Foundation Models and Generative AI, Northwestern University, Evanston, IL 60208, USA · Department of Electrical Engineering, National Taiwan University, Taipei 10617, Taiwan · Department of Physics, National Taiwan University, Taipei 10617, Taiwan +1

  30. Hierarchical Discrete Flow Matching for Graph Generation

    Mar 31, 2026Yoann Boget, Pablo Strasser, Alexandros KalousisGraph GenerationFlow-Based Generative Modeling

    Department of Computer Science, University of Geneva, Switzerland · DMML Group, Geneva School for Business administration HES-SO, Switzerland