Flow-Based Generative Modeling

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

619 papers57 papers in the last four weeks, down 57% on the four weeks before. 0.4% of all new papers.

  1. Low-Dimensional Adaptation of Rectified Flow: A Diffusion and Stochastic Localization Perspective

    Jan 21, 2026Saptarshi Roy, Alessandro Rinaldo, Purnamrita SarkarRectified FlowDiffusion Model Sampling

  2. GRASP: Guided Residual Adapters with Sample-wise Partitioning

    Dec 1, 2025Felix Nützel, Mischa Dombrowski, Bernhard KainzImage GenerationAdapter Tuning

  3. Test-time scaling of diffusions with flow maps

    Nov 27, 2025Amirmojtaba Sabour, Michael S. Albergo, Carles Domingo-Enrich +4Diffusion Model GuidanceDiffusion Guidance

  4. Score-Regularized Joint Sampling with Importance Weights for Flow Matching

    Nov 21, 2025Xinshuang Liu, Runfa Blark Li, Shaoxiu Wei +1Flow MatchingImportance Sampling

  5. Learning Robust Visuomotor Policies via Dynamics Alignment

    Oct 31, 2025Dohyeok Lee, Jung Min Lee, Munkyung Kim +7Visuomotor Policy LearningFlow-Based Policy Learning

  6. PitchFlower: A flow-based neural audio codec with pitch controllability

    Oct 29, 2025Diego Torres, Axel Roebel, Nicolas ObinNeural Audio CodecsControllable Speech Generation

  7. AlignFlow: Improving Flow-based Generative Models with Semi-Discrete Optimal Transport

    Oct 16, 2025Lingkai Kong, Molei Tao, Yang Liu +4Generative ModelingFlow-Based Generative Modeling

  8. Transport-Coupled Bayesian Flows for Molecular Graph Generation

    Oct 11, 2025Yida Xiong, Jiameng Chen, Kun Li +4Molecular Graph GenerationMolecular Generation

  9. ESS-Flow: Training-free guidance as Bayesian inference in source space

    Oct 7, 2025Adhithyan Kalaivanan, Zheng Zhao, Jens Sjölund +1Inference-Time GuidanceConditional Generative Modeling

  10. Predictive Feature Caching for Training-free Acceleration of Molecular Geometry Generation

    Oct 6, 2025Johanna Sommer, John Rachwan, Nils Fleischmann +2Flow MatchingEfficient Inference

  11. Space Group Conditional Flow Matching

    Sep 28, 2025Omri Puny, Yaron Lipman, Benjamin Kurt MillerCrystal Structure GenerationCrystal Structure Prediction

  12. Stochastic Interpolants via Conditional Dependent Coupling

    Sep 27, 2025Chenrui Ma, Xi Xiao, Tianyang Wang +2Generative ModelingDiffusion-Based Image Generation

  13. OT-MeanFlow3D: Bridging Optimal Transport and Meanflow for Efficient 3D Point Cloud Generation

    Sep 26, 2025Elaheh Akbari, Shansita Sharma, Ping He +5Point Cloud GenerationFlow-Based Generative Modeling

  14. Normalizing Flows are Capable Models for Continuous Control

    May 29, 2025Raj Ghugare, Benjamin EysenbachNormalizing FlowsReinforcement Learning

  15. Local Flow Matching Generative Models

    Oct 3, 2024Chen Xu, Xiuyuan Cheng, Yao XieFlow MatchingGenerative Modeling

  16. Robustness and Structure Preservation in Flow-Based Generative Models via Wasserstein Path-Space Divergences

    Oct 2, 2024Ziyu Chen, Markos A. Katsoulakis, Benjamin J. ZhangFlow MatchingEquivariant Neural Networks

  17. Gaussian-Channel Regularity and Distribution Learning with Flow Matching

    Mar 31, 2024Yuan Gao, Jian Huang, Yuling Jiao +1Flow-Based Generative ModelingStatistical Learning Theory

  18. Deep conditional distribution learning via conditional Föllmer flow

    Feb 2, 2024Jinyuan Chang, Zhao Ding, Yuling Jiao +2Conditional Distribution EstimationFlow-Based Generative Modeling

  19. Expected flow networks in stochastic environments and two-player zero-sum games

    Oct 4, 2023Marco Jiralerspong, Bilun Sun, Danilo Vucetic +4Game-Playing AgentsZero-Sum Games