Overview

Flow matching learns a velocity field that moves samples from a simple source, often Gaussian noise, toward a target data distribution. Conditional flow matching trains the field on paths between source and data samples, while optimal-transport couplings and rectified paths aim to make those trajectories easier to learn and integrate with an ordinary differential equation solver. Extensions handle discrete data, curved manifolds and symmetries, physical constraints, and applications from image and speech generation to robotics, scientific forecasting, and inverse problems. A central challenge is getting high fidelity and diverse, reliable samples with few solver steps; theory on convergence and stability is advancing, but the best paths, source distributions, and schedules depend on the task.

Latest papers

CardsList

707 papers53 papers in the last four weeks, down 60% on the four weeks before. 0.4% of all new papers.

  1. Flow Matching from Non-Gaussian Sources: A Theory of Efficient Sampling

    Nov 19, 2026Yuchen Zhou, Lili Zheng, Yuxin Chen +1Flow MatchingFlow-Based Generative Modeling

  2. TrajCal: Trajectory-Calibrated Time Schedules for Few-Step Flow Sampling

    Nov 19, 2026Junchi Zhang, Zihan Gu, Jiangcan Jia +3Flow-Based Generative ModelingFlow Matching

  3. WAMotor: Accelerating World Action Models via Speculative Inference under Dual Nonuniform Denoising Dynamics

    Nov 19, 2026Zexun Lin, Yuan Feng, Xike XieEfficient Inference for World Action ModelsWorld Action Models

  4. Horizontal Flow Matching for Single-Cell Spatiotemporal Dynamics

    Nov 18, 2026Zihan Wang, Jianzhe Li, Zhenyi Zhang +1Flow MatchingSpatial Transcriptomics

  5. Geometry-bridge flow matching for blind rigid-motion correction in head cone-beam CT

    Nov 18, 2026Sungho Yun, Seungryong ChoImage ReconstructionCone-Beam CT

  6. Correcting Flows with Marginal Matching

    Nov 17, 2026Meital Bojan, Nadav Bojan Sellam, Ev Zisselman +1Flow MatchingFlow-Based Generative Modeling

  7. The Limits of Closed-Form Couplings for Few-Step Generation

    Nov 16, 2026Tobias Höppe, Stefan Bauer, Qiang Liu +2Flow-Based Generative ModelingFlow Matching

  8. MetricHand: Geometry-Aware Flow Matching for 4D Hand Reconstruction in Metric World Space

    Nov 16, 2026Yibo Bai, Likui Zhang, Jinglei Zhang +44D Reconstruction3D Hand Reconstruction

  9. Multi-Rate Flow Matching for Point Cloud Upsampling

    Nov 16, 2026Jingkai Shang, Edgar Torres, Duy NguyenPoint Cloud LearningFlow Matching

  10. Flow Matching for Sampled-Data Control of Angular Distributions

    Nov 16, 2026Xin Mao, Anqi Dong, Hongteng Xu +1Flow MatchingMean Flow

  11. Residual-Tail-Informed Flow Matching for Time Series Anomaly Detection

    Nov 15, 2026Shyam Sundar Saravanan, Tie Luo, Sanjay MadriaUnsupervised Anomaly DetectionTime-Series Anomaly Detection

  12. MOUSSE: Multilingual Overlapped Speech Separation with Predictive Uncertainty Estimation

    Nov 15, 2026Su Yeon Shim, Yejin Jeon, David Ifeoluwa Adelani +1Speech SeparationFlow Matching

  13. Explicit Regularization for Flow Matching

    Nov 14, 2026Lars Ruthotto, Eran TreisterFlow MatchingFlow-Based Generative Modeling

  14. Learning Anisotropic Prediction Targets for Flow Models

    Nov 13, 2026Rayhan Zirvi, Hansheng Chen, Gordon Wetzstein +1Flow-Based Generative ModelingFlow Matching

  15. Manifold Attracting Flow Matching: Physics-Constrained Sampling via Continuous Geometric Dynamics

    Nov 12, 2026Guanyu Chen, Jinchen Wang, Shengze Xu +4Constrained Flow MatchingConstrained Generative Modeling

  16. UniFlow-RS: Unified Generative Prediction for Heterogeneous Remote-Sensing Tasks

    Nov 10, 2026Jianlong He, Liang Liao, Jing Xiao +2Remote SensingMulti-Task Dense Prediction

  17. Lipschitz-Controlled Flow Matching for Robust Image Restoration

    Nov 10, 2026Sedjro Salomon Hotegni, Konstantin Sonntag, Paul-Christian Bürkner +1Flow MatchingImage Restoration

  18. FlashMotion: Ultra-Fast Long-Term 3D Motion Generation

    Nov 10, 2026Kaixing Yang, Xulong Tang, Ronghui Li +10Human Motion GenerationText-to-Motion Generation

  19. Robust Flow Matching under Target Corruption and Label Noise

    Nov 9, 2026Mert Can Kurucu, Erik Englesson, Hossein AzizpourFlow MatchingLearning with Noisy Labels

  20. What kills vv-prediction? A Patch-wise PCA Perspective on Pixel-Space Flow Matching

    Nov 9, 2026Tianze Luo, Haofeng Huang, Yuan YaoFlow MatchingDiffusion Transformer

  21. InfCoiL: Coordinated Planner-Controller Learning for Closed-Loop Physics-Based Human-Object Interaction

    Nov 8, 2026Yude Zou, Yifei Yao, Yiwei Hao +2HOI GenerationGoal-Conditioned Planning

  22. EbbFlow: PINN-Inspired Progressive Curriculum for MeanFlow Training

    Nov 8, 2026Mengfan Yuan, Xunheng Kuang, Jianbin Chen +1Flow-Based Generative ModelingFlow Matching

  23. CoupledFlow: One-Step Neural Operators for Coupled Multi-Physics PDEs

    Nov 7, 2026Trong Khiem Tran, Minh Long Bui, Phi Le Nguyen +4Constrained Flow MatchingPDE Solving

  24. Decoupling Direction and Magnitude: Language-Steered Flow Matching for Super-Resolution in the Dark

    Nov 7, 2026Jiaxin Gao, Ziyu Yue, Yaohua Liu +3Image Super-ResolutionDegradation-Aware Image Restoration

  25. PoseRieFlow: Riemannian Flow Matching for Whole-Body Text-to-Pose Generation

    Nov 6, 2026Jan Spindler, Bardia Ardakanian, Patrick Stotko +1Text-to-3D GenerationFlow Matching

  26. ChainFlow: Few-Step Latent Flow Matching for Speculative Decoding

    Nov 5, 2026Selim Aktas, Yusuf Erdem Erdem, Ahmed Zeer +3Speculative DecodingLLM Inference Acceleration

  27. Expanding the Quality-Coverage Frontier with Competitive Flow Matching

    Nov 4, 2026Wenxuan Peng, Richard Zhang, Haitian Zheng +6Generative ModelingFlow Matching

  28. VA-TDM: A Unified View for Improving Few-Step Diffusion Models by Velocity Adversarial Distillation

    Nov 4, 2026Yihong Luo, Tianyu Pang, Tianyang HuDiffusion Model DistillationFew-Step Diffusion Sampling