Flow-Based Generative Modeling

Ask about this topic

Overview

Flow-based generative modeling represents generation as a transformation of probability mass, often by integrating a continuous-time velocity field from noise to data or composing invertible normalizing-flow layers. Flow matching and rectified flow train velocity fields by regression along selected paths; optimal-transport couplings, stochastic interpolants, discrete Markov flows, and flow maps extend the toolkit to different data types and sampling budgets. Researchers apply these methods to images, language, molecules, physical fields, and robot actions, assessing fidelity and diversity alongside likelihood, constraint satisfaction, calibration, and runtime. A central challenge is achieving one- or few-step generation without sacrificing quality or mode coverage, while improving path design, robustness, geometric and physical consistency, and theoretical guarantees.

Latest papers

CardsList

563 papers125 papers in the last four weeks, up 131% on the four weeks before. 0.7% of all new papers.

  1. Divergence is Uncertainty: A Closed-Form Posterior Covariance for Flow Matching

    May 1, 2026Jiarui Xing, Song Wang, Jian WangFlow MatchingUncertainty Quantification

    Yale University · Harvard Medical School

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

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

  3. A unified perspective on fine-tuning and sampling with diffusion and flow models

    Apr 30, 2026Carles Domingo-Enrich, Yuanqi Du, Michael S. AlbergoStochastic Optimal ControlDiffusion Sampling

    Microsoft Research New England · Harvard University, Kempner Institute

  4. How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance

    Apr 29, 2026Jerry Y. Huang, Justin Lin, Sheel Shah +2Generative ModelingFlow-Based Generative Modeling

    Carnegie Mellon University

  5. FlowS: One-Step Motion Prediction via Local Transport Conditioning

    Apr 28, 2026Leandro Di Bella, Adrian Munteanu, Bruno CornelisFlow MatchingTrajectory Generation

    Department of Electronics and Informatics, Vrije Universiteit Brussel, Pleinlaan 2, B-1050 Brussels, Belgium. · IMEC, Kapeldreef 75, B-3001 Leuven, Belgium.

  6. CoreFlow: Low-Rank Matrix Generative Models

    Apr 27, 2026Dongze Wu, Linglingzhi Zhu, Yao XieGenerative ModelingContinuous Normalizing Flows

    H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA

  7. FlowPlace: Flow Matching for Chip Placement

    Apr 26, 2026Peng Xie, Ke Xue, Yunqi Shi +6Constrained Generative ModelingFlow Matching

    1State Key Laboratory of Novel Software Technology, Nanjing University, China · School of Artificial Intelligence, Nanjing University, China · 3Huawei Noah’s Ark Lab, China

  8. MotionHiFlow: Text-to-motion via hierarchical flow matching

    Apr 25, 2026Heng Li, Xiaotong Lin, Ling-An Zeng +3Flow MatchingText-to-Motion Generation

    Sun Yat-sen University · Shandong University · Guangdong Province Key Laboratory of Information Security Technology, China +1

  9. Normalizing Flows with Iterative Denoising

    Apr 21, 2026Tianrong Chen, Jiatao Gu, David Berthelot +2Normalizing FlowsAutoregressive Image Generation

    Apple Machine Learning Research.

  10. Frequency-Forcing: From Scaling-as-Time to Soft Frequency Guidance

    Apr 21, 2026Weitao DuFlow MatchingImage Generation

    DAMO Academy

  11. Prior-Fitted Functional Flow: In-Context Generative Models for Pharmacokinetics

    Apr 19, 2026César Ojeda, Niklas Hartung, Wilhelm Huisinga +6Probabilistic Time Series ForecastingHealthcare

    University of Potsdam, Germany · Technical University Berlin, Germany · Freie Universität Berlin, Germany +2

  12. FlowC2S: Flowing from Current to Succeeding Frames for Fast and Memory-Efficient Video Continuation

    Apr 19, 2026Hovhannes Margaryan, Quentin Bammey, Christian SandorFlow MatchingT2V Generation

    Team ARAI, Universit´e Paris-Saclay, CNRS, LISN, France · LTCI, T´el´ecom Paris, Institut Polytechnique de Paris, France

  13. The Amazing Stability of Flow Matching

    Apr 17, 2026Rania Briq, Michael Kamp, Ohad Fried +2Flow MatchingGenerative Modeling

    Forschungszentrum Jülich · TU Dortmund · Lamarr Institute +4

  14. Frequency-Aware Flow Matching for High-Quality Image Generation

    Apr 16, 2026Sucheng Ren, Qihang Yu, Ju He +3Flow MatchingConditional Image Generation

    Johns Hopkins University · ByteDance

  15. One-Shot Generative Flows: Existence and Obstructions

    Apr 16, 2026Panos Tsimpos, Daniel Sharp, Youssef MarzoukFlow MatchingOne-Step Generative Modeling

    Operations Research Center · Massachusetts Institute of Technology · Cambridge, MA 02139 +2

  16. LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories

    Apr 16, 2026Zhanhao Liang, Tao Yang, Jie Wu +2Diffusion Model AlignmentFlow Matching

    1The Australian National University · 2ByteDance Seed

  17. Towards Faster Language Model Inference Using Mixture-of-Experts Flow Matching

    Apr 16, 2026Aihua LiNon-Autoregressive Text GenerationFlow Matching

    Duke University

  18. PRiMeFlow: Capturing Complex Expression Heterogeneity in Perturbation Response Modelling

    Apr 15, 2026Zichao Yan, Yan Wu, Mica Xu Ji +10Single-Cell Perturbation ModelingSingle-Cell Transcriptomics

    Altos Labs · Current affiliation: Verge Genomics · Current affiliation: Loka +1

  19. EMGFlow: Robust and Efficient Surface Electromyography Synthesis via Flow Matching

    Apr 15, 2026Boxuan Jiang, Chenyun Dai, Can HanSynthetic Data AugmentationConditional Generative Modeling

    School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China

  20. PianoFlow: Music-Aware Streaming Piano Motion Generation with Bimanual Coordination

    Apr 14, 2026Xuan Wang, Kai Ruan, Jiayi Han +2Human Motion GenerationFlow-Based Generative Modeling

    Zhejiang University Hangzhou, Zhejiang, China · Renmin University of China Beijing, China · Beijing Forestry University Beijing, China +1

  21. SubFlow: Sub-mode Conditioned Flow Matching for Diverse One-Step Generation

    Apr 14, 2026Yexiong Lin, Jia Shi, Shanshan Ye +3Flow MatchingFlow-Based Generative Modeling

    Sydney AI Centre, The University of Sydney, Sydney, NSW, Australia · School of Artificial Intelligence, Xidian University, Xi’an, Shaanxi, China · Australian Artificial Intelligence Institute, University of Technology Sydney, Sydney, NSW, Australia +1

  22. MorphoFlow: Sparse-Supervised Generative Shape Modeling with Adaptive Latent Relevance

    Apr 13, 2026Mokshagna Sai Teja Karanam, Tushar Kataria, Shireen ElhabianStatistical Shape Modeling3D Shape Generation

    Kahlert School of Computing, Scientific Computing and Imaging Institute, University of Utah, Utah, USA

  23. LayerCache: Exploiting Layer-wise Velocity Heterogeneity for Efficient Flow Matching Inference

    Apr 13, 2026Guandong LiFlow MatchingFlow-Based Generative Modeling

    iFLYTEK

  24. Continuous Adversarial Flow Models

    Apr 13, 2026Shanchuan Lin, Ceyuan Yang, Zhijie Lin +2Flow-Based Generative ModelingImage Generation

    ByteDance Seed

  25. Probabilistic Prediction of Neural Dynamics via Autoregressive Flow Matching

    Apr 13, 2026Nicole Rogalla, Yuzhen Qin, Mario Senden +2Functional Magnetic Resonance ImagingProbabilistic Time Series Forecasting

    Department of Machine Learning and Neural Computing, Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, the Netherlands · Department of Cognitive Neuroscience, Maastricht University, Maastricht, the Netherlands · Maastricht Brain Imaging Center, Maastricht University, Maastricht, the Netherlands

  26. FlowCoMotion: Text-to-Motion Generation via Token-Latent Flow Modeling

    Apr 13, 2026Dawei Guan, Di Yang, Chengjie Jin +1Text-to-Motion GenerationHuman Motion Generation

    School of Artificial Intelligence and Data Science, University of Science and Technology of China · Suzhou Institute for Advanced Research, University of Science and Technology of China

  27. MixFlow: Mixed Source Distributions Improve Rectified Flows

    Apr 10, 2026Nazir Nayal, Christopher Wewer, Jan Eric LenssenRectified FlowImage Generation

    Max Planck Institute for Informatics, Saarland Informatics Campus, Germany

  28. Discrete Meanflow Training Curriculum

    Apr 10, 2026Chia-Hong Hsu, Frank WoodFlow-Based Generative ModelingMeanFlow

    Department of Computer Science, University of British Columbia, Vancouver, BC, Canada

  29. 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

  30. Optimal-Transport-Guided Functional Flow Matching for Turbulent Field Generation in Hilbert Space

    Apr 7, 2026Li Kunpeng, Wan Chenguang, Qu Zhisong +5Flow-Based Generative ModelingFlow Matching