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. RAC: Rectified Flow Auto Coder

    Mar 6, 2026Sen Fang, Yalin Feng, Yanxin Zhang +6AutoencodersVariational Autoencoders

  2. RelaxFlow: Text-Driven Amodal 3D Generation

    Mar 5, 2026Jiayin Zhu, Guoji Fu, Xiaolu Liu +3Text-to-3D Generation3D Shape Completion

    National University of Singapore · Zhejiang University · University of Science and Technology of China

  3. Linearized Coupling Flow with Shortcut Constraints for One-Step Face Restoration

    Mar 4, 2026Xiaohui Sun, Hanlin WuImage RestorationFlow Matching

    School of Information Science and Technology, Beijing Foreign Studies University, Beijing 100089, China

  4. Preconditioned Flow Matching

    Mar 2, 2026Shadab Ahamed, Eshed Gal, Md Shahriar Rahim Siddiqui +3Flow MatchingFlow-Based Generative Modeling

    University of British Columbia, Vancouver, Canada · University of Cambridge, Cambridge, United Kingdom

  5. AG-REPA: Causal Layer Selection for Representation Alignment in Audio Flow Matching

    Mar 1, 2026Pengfei Zhang, Tianxin Xie, Minghao Yang +1Flow-Based Generative ModelingFlow Matching

    AI Thrust, Information Hub, The Hong Kong University of Science and Technology (Guangzhou).

  6. Active Flow Matching

    Mar 1, 2026Yashvir S. Grewal, Daniel M. Steinberg, Thang D. Bui +2Molecule DesignFlow-Based Generative Modeling

    School of Computing, College of Systems and Society, Australian National University, Australia · Data61, CSIRO, Australia

  7. Generalizing Score-based generative models for Heavy-tailed Distributions

    Feb 28, 2026Tiziano Fassina, Gabriel Cardoso, Sylvan Le Corff +1Generative ModelingScore-Based Generative Modeling

    STIM, Mines Paris Paris, France · LPSM, Sorbonne Université Paris, France

  8. Flowette: Flow Matching with Graphette Priors for Graph Generation

    Feb 27, 2026Asiri Wijesinghe, Sevvandi Kandanaarachchi, Daniel M. Steinberg +1Graph GenerationFlow-Based Generative Modeling

    CSIRO’s Data61 · Australian National University

  9. ProjFlow: Projection Sampling with Flow Matching for Zero-Shot Exact Spatial Motion Control

    Feb 26, 2026Akihisa Watanabe, Qing Yu, Edgar Simo-Serra +1Human Motion GenerationFlow-Based Generative Modeling

    Waseda University · LY Corporation

  10. Flow Matching is Adaptive to Manifold Structures

    Feb 25, 2026Shivam Kumar, Yixin Wang, Lizhen LinFlow MatchingGenerative Modeling

    Booth School of Business, University of Chicago · Department of Statistics, University of Michigan · Department of Mathematics, University of Maryland, College Park

  11. Entropy-Controlled Flow Matching

    Feb 25, 2026Chika MaduabuchiFlow MatchingFlow-Based Generative Modeling

    William & Mary, Williamsburg, VA, USA

  12. Provably Safe Generative Sampling with Constricting Barrier Functions

    Feb 24, 2026Darshan Gadginmath, Ahmed Allibhoy, Fabio PasqualettiConstrained SamplingConstrained Generative Modeling

    Mitsubishi Electric Research Laboratories Cambridge, Massachusetts · Electrical Engineering and Computer Science University of California, Irvine

  13. A Long-Short Flow-Map Perspective for Drifting Models

    Feb 24, 2026Zhiqi Li, Bo ZhuDrifting ModelsFlow Map Learning

    School of Interactive Computing, Georgia Institute of Technology

  14. Momentum Guidance: Plug-and-Play Guidance for Flow Models

    Feb 23, 2026Runlong Liao, Jian Yu, Baiyu Su +3Momentum MethodsDiffusion Guidance

    The University of Texas at Austin, Austin, TX 78712, USA

  15. MeanFuser: Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via MeanFlow for End-to-End Autonomous Driving

    Feb 23, 2026Junli Wang, Yinan Zheng, Xueyi Liu +9Autonomous Driving PlanningEnd-to-End Autonomous Driving

    SKL-MAIS, Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · Xiaomi EV +1

  16. An LLM-Enabled Frequency-Aware Flow Diffusion Model for Natural-Language-Guided Power System Scenario Generation

    Feb 23, 2026Zhenghao Zhou, Yiyan Li, Fei Xie +5Conditional Generative ModelingPower Systems

    College of Smart Energy, Shanghai Non-Carbon Energy Conversion and Utilization Institute, and Key Laboratory of Control of Power Transmission and Conversion, Ministry of Education, Shanghai Jiao Tong University, Shanghai, 200240, China. · Qinghai Photovoltaic Industry Innovation Center Co., Ltd., State Power Investment Corporation, Xining 810007, China. · Xinjiang Hami Co., Ltd., State Power Investment Corporation, Hami 839000, China. +1

  17. Multimodal Crystal Flow: Any-to-Any Modality Generation for Unified Crystal Modeling

    Feb 23, 2026Kiyoung Seong, Sungsoo Ahn, Sehui Han +1Crystal Structure GenerationUnified Multimodal Models

    Graduate School of AI, KAIST, Seoul, South Korea · Materials Intelligence Lab, LG AI Research, Seoul, South Korea

  18. Laplacian Multi-scale Flow Matching for Generative Modeling

    Feb 23, 2026Zelin Zhao, Petr Molodyk, Haotian Xue +1Mixture-of-TransformersGenerative Modeling

    Georgia Institute of Technology Atlanta, GA 30332, USA

  19. AdsorbFlow: energy-conditioned flow matching enables fast and realistic adsorbate placement

    Feb 22, 2026Jiangjie Qiu, Wentao Li, Honghao Chen +2Flow-Based Generative ModelingMaterials Science

    Beijing Key Laboratory of Artificial Intelligence for Advanced Chemical Engineering Materials, Department of Chemical Engineering, Tsinghua University, Beijing, China.

  20. GenPlanner: From Noise to Plans -- Emergent Reasoning in Flow Matching and Diffusion Models

    Feb 21, 2026Agnieszka Polowczyk, Alicja Polowczyk, Michał WieczorekDiffusion-Based PlanningMotion Planning

    Silesian University of Technology, Faculty of Applied Mathematics, Gliwice, 44-100, Poland

  21. From Static Spectra to Operando Infrared Dynamics: Physics Informed Flow Modeling and a Benchmark

    Feb 20, 2026Shuquan Ye, Ben Fei, Hongbin Xu +2Infrared SpectroscopyPhysics-Informed Generative Modeling

    Department of Information Engineering, The Chinese University of Hong Kong · Shenzhen Loop Area Institute · Massachusetts Institute of Technology +1

  22. Conditional Flow Matching for Continuous Anomaly Detection in Autonomous Driving on a Manifold-Aware Spectral Space

    Feb 19, 2026Antonio Guillen-PerezUnsupervised Anomaly DetectionAutonomous Driving Safety Evaluation

    Independent Researcher

  23. Flow Map Language Models: One-step Language Modeling via Continuous Denoising

    Feb 18, 2026Chanhyuk Lee, Jaehoon Yoo, Manan Agarwal +6Continuous Diffusion Language ModelsOne-Step Generative Modeling

    KAIST · Carnegie Mellon University

  24. MolCrystalFlow: Molecular Crystal Structure Prediction via Flow Matching

    Feb 17, 2026Cheng Zeng, Harry W. Sullivan, Thomas Egg +8Crystal Structure PredictionFlow-Based Generative Modeling

    Department of Chemistry, University of Florida, Gainesville, FL 32611, USA · Quantum Theory Project, University of Florida, Gainesville, FL 32611, USA · Department of Chemical Engineering and Material Science, University of Minnesota - Twin Cities, Minneapolis, MN 55455, USA +6

  25. Verifier-Constrained Flow Expansion for Discovery Beyond the Data

    Feb 17, 2026Riccardo De Santi, Kimon Protopapas, Ya-Ping Hsieh +1Flow-Based Generative ModelingConstrained Generative Modeling

    ETH Zürich · ETH AI Center

  26. Constraining Streaming Flow Models for Adapting Learned Robot Trajectory Distributions

    Feb 17, 2026Jieting Long, Dechuan Liu, Weidong Cai +2Robot Motion GenerationConstrained Motion Planning

    School of Computer Science, The University of Sydney, Australia. · School of Aerospace, Mechanical and Mechatronic Engineering, The University of Sydney, Australia. · Australian Center For Robotics, The University of Sydney, Australia. +1

  27. Rethinking Diffusion Models with Symmetries through Canonicalization with Applications to Molecular Graph Generation

    Feb 16, 2026Cai Zhou, Zijie Chen, Zian Li +7Generative ModelingDiffusion Models

    Massachusetts Institute of Technology · Zhejiang University · Peking University +3

  28. Native Extrapolation Awareness in Flow-Based Conditional Generation

    Feb 13, 2026Constantinos Tsakonas, Serena Ivaldi, Jean-Baptiste MouretFlow MatchingFlow-Based Generative Modeling

    Inria, Université de Lorraine, CNRS, Loria Nancy, France

  29. FAIL: Flow Matching Adversarial Imitation Learning for Image Generation

    Feb 12, 2026Yeyao Ma, Chen Li, Xiaosong Zhang +2Flow MatchingConditional Image Generation

    Shanghai Jiao Tong University · Xi’an Jiaotong University · Tencent

  30. Dual-End Consistency Model

    Feb 11, 2026Linwei Dong, Ruoyu Guo, Ge Bai +3One-Step Generative ModelingConsistency Distillation

    1Zhejiang University · 2Bytedance Inc. · 3Zhejiang Lab