Langevin Flow Maps: Efficient Molecular Dynamics and Transition Path Sampling
Not on the map. Why?
Abstract (arXiv)
Molecular dynamics simulations proceed by integrating the Langevin equations over many small femtosecond timesteps. This poses a challenge for estimating ensemble properties and transition dynamics that occur on much longer timescales. We introduce Langevin Flow Maps, which extend machine-learned force-fields to additionally learn the stochastic Langevin integrator. We show that Langevin Flow Maps enable large-timestep molecular dynamics and recover accurate dynamical properties of the system, while running an order of magnitude faster than current machine-learned force fields. Further, by training on a diverse molecular dataset, we demonstrate a path towards transferable Langevin Flow Maps.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 50 references that are in the map. First posted on arXiv 5 Oct 2026.
Builds on
34 of 50 references.
References · 34
- 2025Mean Flows for One-step Generative Modelingcited by 561
- 2024One Step Diffusion via Shortcut Modelscited by 391
- 2020Scalable Gradients for Stochastic Differential Equationscited by 271
- 2020Machine Learning Force Fieldscited by 207
- 2021Neural SDEs as Infinite-Dimensional GANscited by 161
- 2023Equivariant flow matchingcited by 135
- 2019Machine learning for molecular simulationcited by 110
- 2024Flow map matching with stochastic interpolants: A mathematical framework for consistency modelscited by 109
- 2021SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effectscited by 104
- 2025How to build a consistency model: Learning flow maps via self-distillationcited by 103
- 2022Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulationscited by 95
- 2023Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamicscited by 66
22 more
- 2021Smooth Normalizing Flowscited by 53
- 2024Transferable Boltzmann Generatorscited by 46
- 2021Learning effective stochastic differential equations from microscopic simulations: linking stochastic numerics to deep learningcited by 39
- 2021Deeptime: a Python library for machine learning dynamical models from time series datacited by 38
- 2025Scalable Equilibrium Sampling with Sequential Boltzmann Generatorscited by 38
- 2023Non-adversarial training of Neural SDEs with signature kernel scorescited by 37
- 2026Meta Flow Maps enable scalable reward alignmentcited by 37
- 2026Diamond Maps: Efficient Reward Alignment via Stochastic Flow Mapscited by 29
- 2024Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Samplingcited by 27
- 2020A reinforcement learning approach to rare trajectory samplingcited by 22
- 2025Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functionalcited by 20
- 2021Reinforcement learning of rare diffusive dynamicscited by 15
- 2025Force-Free Molecular Dynamics Through Autoregressive Equivariant Networkscited by 15
- 2025FlashMD: long-stride, universal prediction of molecular dynamicscited by 12
- 2025Amortized Sampling with Transferable Normalizing Flowscited by 12
- 2025Transferable Generative Models Bridge Femtosecond to Nanosecond Time-Step Molecular Dynamicscited by 11
- 2023Differentiable Simulations for Enhanced Sampling of Rare Eventscited by 8
- 2025Efficient Regression-Based Training of Normalizing Flows for Boltzmann Generatorscited by 8
- 2026Learning Hamiltonian Flow Maps: Mean Flow Consistency for Large-Timestep Molecular Dynamicscited by 7
- 2026Strong Stochastic Flow Mapscited by 6
- 2025Neural Stochastic Flows: Solver-Free Modelling and Inference for SDE Solutionscited by 5
- 2024On the design space between molecular mechanics and machine learning force fieldscited by 4
Built on by
Not cited yet.