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

38 papers6 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

  1. CupOFMoCA: Coupled Objective-Guided Discrete Flows for Molecular Conjugate Assembly

    Nov 11, 2026Ruoxi Rosie Zhang, Ziang Li, Jiatao Gu +1Molecular GenerationDrug Discovery

  2. JoVox: Joint Hierarchical Flow Matching for Lightweight Voxel Generation

    Nov 7, 2026Xiangjun Tang, Jianqi Chen, Peter WonkaGenerative Modeling3D Shape Generation

  3. UniFlow: Unified Multi-Scale Flow Matching for Time Series Generation

    Nov 3, 2026Shibo Feng, Wei Li, Songhua Liu +3Time Series GenerationFlow-Based Generative Modeling

  4. Beyond Reachability: When Edit Order Preserves Couplings in Graph Flow Matching

    Oct 28, 2026Zilin Li, Zixing SongGraph GenerationFlow Matching

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

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

  6. Trajectory Matching: Discrete Flow Matching with Structured Actions

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

  7. When Do Discrete Actions Make Good Continuous Controllers?

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

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

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

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

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

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

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

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

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

  12. 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 +3Entropy-Based DecodingFlow-Based Generative Modeling

  13. 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

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

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

  15. Context-weighted Discrete Flow Matching

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

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

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

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

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

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

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

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

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

  20. 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

  21. 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

  22. Flexible Flows for Biological Sequence Design

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

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

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

  24. 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

  25. Discrete Flow Matching: Convergence Guarantees Under Minimal Assumptions

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

  26. 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

  27. Scaling Categorical Flow Maps

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

  28. Tree-Conditioned Edit Flows for Ancestral Sequence Reconstruction

    May 5, 2026Emil Sharafutdinov, Ingemar AndréFlow MatchingPhylogenetic Inference