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. Attention-Guided Flow-Matching for Sparse 3D Geological Generation

    Apr 7, 2026Zhixiang Lu, Mengqi Han, Peixin Guo +4Flow-Based Generative ModelingFlow Matching

    Xi’an Jiaotong-Liverpool University, Jiangsu 215123, China · Deep Optica, Shanghai 200030, China · University of Chinese Academy of Sciences, Beijing 100049, China

  2. Generative Path-Law Jump-Diffusion: Sequential MMD-Gradient Flows and Generalisation Bounds in Marcus-Signature RKHS

    Apr 6, 2026Daniel BlochFlow-Based Generative ModelingStochastic Differential Equations

    UNIVERSITY OF PARIS 6 & VINUNIVERSITY · Visting Professor at the College of Engineering and Computer Science, VinUniversity, Hanoi.

  3. Training-Free Refinement of Flow Matching with Divergence-based Sampling

    Apr 6, 2026Yeonwoo Cha, Jaehoon Yoo, Semin Kim +3Flow MatchingT2I Generation

    KAIST

  4. FlowLM: Few-Step Language Modeling via Diffusion-to-Flow Adaptation

    Apr 6, 2026Runzhe Zhang, Letian Chen, Wenpeng Zhang +2Language ModelingFlow-Based Generative Modeling

    Shanghai Jiao Tong University · ByteDance

  5. Isokinetic Flow Matching for Pathwise Straightening of Generative Flows

    Apr 6, 2026Tauhid KhanFlow MatchingFlow-Based Generative Modeling

  6. FAVE: Flow-based Average Velocity Establishment for Sequential Recommendation

    Apr 6, 2026Ke Shi, Yao Zhang, Feng Guo +4Sequential RecommendationGenerative Recommendation

    University of Electronic Science and Technology of China · State Key Laboratory of Internet Architecture

  7. Beyond Fixed Inference: Quantitative Flow Matching for Adaptive Image Denoising

    Apr 2, 2026Jigang Duan, Genwei Ma, Xu Jiang +3Image DenoisingFlow Matching

    School of Mathematical Sciences, Capital Normal University, Beijing 100048, China · National Center for Applied Mathematics Beijing, Capital Normal University and Academy for multidisciplinary studies, Capital Normal University, Beijing, 100048, China · Institute of Nuclear and New Energy Technology, Tsinghua University, Beijing 100084, China

  8. SteerFlow: Steering Rectified Flows for Faithful Inversion-Based Image Editing

    Apr 2, 2026Thinh Dao, Zhen Wang, Kien T. Pham +1Text-Guided Image EditingFlow-Based Generative Modeling

    The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong · VinUniversity, Ha Noi, Viet Nam

  9. Flow Learners for PDEs: Toward a Physics-to-Physics Paradigm for Scientific Computing

    Apr 2, 2026Yilong Dai, Shengyu Chen, Xiaowei Jia +1Neural PDE SolversPDE Solving

    The University of Alabama, Tuscaloosa, Alabama, USA · University of Pittsburgh, Pittsburgh, Pennsylvania, USA

  10. EgoFlow: Gradient-Guided Flow Matching for Egocentric 6DoF Object Motion Generation

    Apr 1, 2026Abhishek Saroha, Huajian Zeng, Xingxing Zuo +2Egocentric Video UnderstandingFlow-Based Generative Modeling

    TU München · MCML · MBZUAI +1

  11. 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

  12. Stepwise Credit Assignment for GRPO on Flow-Matching Models

    Mar 30, 2026Yash Savani, Branislav Kveton, Yuchen Liu +5RL for Diffusion ModelsStep-Level Credit Assignment in RL

    Carnegie Mellon University · Adobe Research

  13. ConceptWeaver: Weaving Disentangled Concepts with Flow

    Mar 30, 2026Jintao Chen, Aiming Hao, Xiaoqing Chen +6Subject-Driven Image GenerationCompositional Image Generation

    Peking University · AMAP, Alibaba Group

  14. HiFlow: Tokenization-Free Scale-Wise Autoregressive Policy Learning via Flow Matching

    Mar 28, 2026Daichi Yashima, Koki Seno, Shuhei Kurita +2Visuomotor Policy LearningFlow-Based Policy Learning

    Keio University · National Institute of Informatics Research and Development Center for Large Language Models · National Institute of Informatics

  15. Hierarchy-Guided Topology Latent Flow for Molecular Graph Generation

    Mar 28, 2026Urvi Awasthi, Alexander Arjun Lobo, Leonid ZhukovMolecular Graph Generation3D Molecular Generation

    BCG X AI Science Institute

  16. Unified Number-Free Text-to-Motion Generation Via Flow Matching

    Mar 27, 2026Guanhe Huang, Oya CeliktutanText-to-Motion GenerationHuman Motion Generation

    King’s College London

  17. Property-Guided Molecular Generation and Optimization via Latent Flows

    Mar 27, 2026Alexander Arjun Lobo, Urvi Awasthi, Leonid ZhukovMolecular GenerationMolecular Optimization

    BCG X AI Science Institute

  18. GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow

    Mar 27, 2026Ziyue Zeng, Xun Su, Haoyuan Liu +3Video CompressionGenerative Video Compression

    Graduate School of Fundamental Science and Engineering, Waseda University, Tokyo, Japan

  19. LILAC: Language-Conditioned Object-Centric Optical Flow for Open-Loop Trajectory Generation

    Mar 26, 2026Motonari Kambara, Koki Seno, Tomoya Kaichi +2Language-Conditioned Robot ManipulationRobot Motion Generation

    Keio University · KDDI Research Inc.

  20. TIGFlow-GRPO: Trajectory Forecasting via Interaction-Aware Flow Matching and Reward-Guided Optimization

    Mar 26, 2026Xuepeng Jing, Wenhuan Lu, Hao Meng +2Trajectory PredictionPedestrian Trajectory Prediction

    Tianjin University, Tianjin, China

  21. Marchuk: Efficient Global Weather Forecasting from Mid-Range to Sub-Seasonal Scales via Flow Matching

    Mar 25, 2026Arsen Kuzhamuratov, Mikhail Zhirnov, Andrey Kuznetsov +2Weather ForecastingSpatiotemporal Forecasting

    AXXX · FusionBrain Lab

  22. OsteoFlow: Lyapunov-Guided Flow Distillation for Predicting Bone Remodeling after Mandibular Reconstruction

    Mar 23, 2026Hamidreza Aftabi, Faye Yu, Brooke Switzer +6Longitudinal Medical Image AnalysisFlow-Based Generative Modeling

    Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, British Columbia, Canada · Sunnybrook Research Institute, University of Toronto, Toronto, Ontario, Canada · Department of Mechanical Engineering, University of British Columbia, Vancouver, British Columbia, Canada +1

  23. From Diffusion to Flow: Efficient Motion Generation in MotionGPT3

    Mar 23, 2026Jaymin Bhan, JiHong Jeon, SangYeop JeongText-to-Motion GenerationMotion Diffusion Models

    Department of Applied Artificial Intelligence Seoul National University of Science and Technology

  24. SetFlow: Generating Structured Sets of Representations for Multiple Instance Learning

    Mar 20, 2026Nikola Jovišić, Milica Škipina, Vanja ŠvendaGenerative ModelingSynthetic Data Augmentation

    Institute for Artificial Intelligence R&D of Serbia Novi Sad, Serbia

  25. DynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous Driving

    Mar 20, 2026Xiaolu Liu, Yicong Li, Song Wang +3World Models for Autonomous DrivingLatent World Models

    Zhejiang University · National University of Singapore

  26. Warm-Start Flow Matching for Guaranteed Fast Text/Image Generation

    Mar 19, 2026Minyoung KimFlow MatchingFlow-Based Generative Modeling

    Samsung AI Center Cambridge, United Kingdom

  27. Few-shot Acoustic Synthesis with Multimodal Flow Matching

    Mar 19, 2026Amandine BrunettoAudio GenerationSpatial Audio

    Center for Robotics, Mines Paris - PSL University

  28. InjectFlow: Weak Guides Strong via Orthogonal Injection for Flow Matching

    Mar 19, 2026Dayu Wang, Jiaye Yang, Weikang Li +2Flow MatchingFlow-Based Generative Modeling

    Baidu Inc. · Peking University

  29. Few-Step Diffusion Sampling Through Instance-Aware Discretizations

    Mar 18, 2026Liangyu Yuan, Ruoyu Wang, Tong Zhao +4Few-Step Diffusion SamplingDiffusion Timestep Scheduling

    Westlake University · Tongji University · Zhejiang University +1

  30. Large-Scale 3D Ground-Motion Synthesis with Physics-Inspired Latent Operator Flow Matching

    Mar 18, 2026Yaozhong Shi, Grigorios Lavrentiadis, Konstantinos Tsalouchidis +5Physics-Informed Generative ModelingSeismology

    Division of Engineering and Applied Sciences, California Institute of Technology, Pasadena, CA, USA · School of Engineering and Applied Sciences, University at Buffalo, Buffalo, NY, USA · Lawrence Berkeley National Laboratory, Berkeley, CA, USA +2