Flow Map Learning

Also known as MAP

Overview

Flow map learning studies how to predict a system’s finite-time transition—from one state or distribution to another—rather than repeatedly integrating a local velocity field. Approaches include semigroup-consistency objectives such as MeanFlow, optimal-transport flow matching, stochastic flow maps for SDEs, and distillation of slow teachers into few-step generators; neural operators and physical or geometric constraints adapt the idea to PDEs, molecular dynamics, and control. Applications range from one-step image and text generation to long-horizon forecasting, inverse problems, and molecular simulation. A central tension is making large, few-step transitions accurate and stable while preserving physical structure and generalization across step sizes or unseen conditions; theory for training stability and out-of-distribution behavior remains uneven.

Latest papers

CardsList

53 papers6 papers in the last four weeks, down 54% on the four weeks before. 0.0% of all new papers.

  1. Kolmogorov-Chapman Maps: Trajectory-Free Learning for Simulating Molecular Dynamics

    Nov 9, 2026Majdi Hassan, Marta Skreta, Dominique Beaini +1Stochastic Differential EquationsMolecular Dynamics Simulation

  2. CoReFlow: Consistency-Relaxed Flow Maps for Probabilistic Traffic Forecasting

    Nov 3, 2026Pengnan Chi, Zhiguo Zhang, Xiaoliang MaProbabilistic ForecastingTraffic Forecasting

  3. Asynchronous Flow Map Language Models

    Oct 30, 2026Chanhyuk Lee, Wonjung Kim, Patrick Pynadath +5Language ModelingOne-Step Generative Modeling

  4. Model reduction in time: Learning flow maps for reducing stochastic dynamical systems in time

    Oct 26, 2026Shreya Jha, Benjamin PeherstorferReduced-Order ModelingFlow Map Learning

  5. Improved Training of Strong Stochastic Flow Maps

    Oct 21, 2026Zander W. Blasingame, Antonio Franca, Raul Minan +3Flow Map LearningStochastic Differential Equations

  6. Normalizing Flow Maps

    Oct 15, 2026Francesco M. Ruscio, Timothy James Hitge, Fred Zhangzhi Peng +6Normalizing FlowsFlow Map Learning

  7. On the Stability and Convergence of Flow Map Training

    Oct 14, 2026Ishan Nath, Tom Stanic, Avishek Joey Bose +2Flow Map LearningNeural Network Training Dynamics

  8. Flow-of-Thought: A Framework for Visual Reasoning

    Oct 7, 2026Mariia Baidachna, Nicolas PugeaultVisual ReasoningSpatial Reasoning

  9. Geometry-Aware Time Reparameterization for Flow-Map Distillation

    Oct 1, 2026Félix Dedek, Makoto YamadaFlow-Based Generative ModelingFlow Map Learning

  10. Gumbel Straight Flow: Distilling Autoregressive Models into One-step Flow Maps

    Sep 30, 2026Yeongmin Kim, Arnaud Doucet, Andrew Campbell +3Non-Autoregressive Text GenerationOne-Step Generative Modeling

  11. MeanFlowAdvantage: Stable Reward Fine-Tuning for Few-Step Average-Velocity Generators

    Sep 29, 2026Haocheng Tang, Tianchi Xie, Xingqiao LinFlow MatchingMeanFlow

  12. Learning the Structure of Triangular Transport Maps

    Sep 29, 2026Morten Blørstad, Pekka Parviainen, Berent Ånund Strømnes LundeFlow Map LearningDensity Estimation

  13. Physics-Guided Flow-Map Matching for Precipitation Nowcasting

    Sep 27, 2026Shunya Nagashima, Takumi Bannai, Makoto Misaizu +3Precipitation NowcastingConditional Generative Modeling

  14. Bridging Stochastic Flow Maps and Boltzmann Generators with Normalizing Flows

    Sep 25, 2026Louis Grenioux, RuiKang OuYang, Luhuan WuBoltzmann SamplingMolecular Generation

  15. Kairos: Grounded Forecasting of Presence and Directional Flow in 4D Scene Graphs

    Sep 23, 2026Iacopo Catalano, Julio A. Placed, Javier Civera +1Spatiotemporal ForecastingProbabilistic Forecasting

  16. Stochastic Flow Map for Count Data

    Sep 20, 2026Ganchao WeiSynthetic Data GenerationOne-Step Generative Modeling

  17. CyclOT: Learning Quadratic Optimal Transport Maps via Synchronized Forward-Backward Interpolants

    Sep 12, 2026Shizhou Xu, Jiachen Liu, Shih-Hsin Wang +4Cycle ConsistencyOptimal Transport

  18. Introductory Notes on Learning2^2

    Sep 6, 2026Sai Siddharth, Maniarasu RaviPhysics-Informed MLDynamical Systems

  19. Accelerating Chemical Kinetics for Exoplanet Atmospheres using Neural Networks

    Aug 31, 2026Isaac Malsky, Xi Zhang, Tiffany Kataria +5Neural Surrogate ModelingFlow Map Learning

  20. Physics-Constrained Neural Flow Maps for Long-Horizon Prediction of Spin Dynamics

    Aug 22, 2026Haoen Feng, Shenglan Yuan, Shirong LinFlow Map LearningPhysics-Informed ML

  21. From Fixed Grids to Moving Particles:A Transferable Latent Operator for Fluid Dynamics

    Aug 14, 2026Meng Li, Chuqi Chen, Zhengqing Gao +4Neural OperatorsComputational Fluid Dynamics

  22. Flow-Map Distillation on Relation Manifolds for Image Restoration

    Aug 6, 2026Zihao He, Songhua LiuFlow MatchingFlow Map Learning

  23. Modeling Unknown Nonlocal PDE Systems via Flow Map Learning

    Aug 1, 2026Zhongshu Xu, Ying Li, Yanzhi Zhang +1PDE Surrogate ModelingFlow Map Learning

  24. Latent-Kernel Discrete Flow Maps for Few-Step Generation

    Jul 29, 2026Mansoor Ahmed, Yue-Tsz Fan, Hemanth Venkateswara +1Latent Variable ModelsFew-Step Diffusion Sampling