arXiv：cs.LG· Sam McCallum, Niklas Rindtorff, Alexander Tong, James Foster·· 7 小时前
Langevin Flow Maps：高效分子动力学与过渡路径采样
Langevin Flow Maps: Efficient Molecular Dynamics and Transition Path Sampling
AI 导读
Langevin Flow Maps 将机器学习的力场扩展为同时学习随机 Langevin 积分器，支持大时间步分子动力学并准确还原系统动力学性质，运行速度比现有机器学习力场快一个数量级。通过在多样化分子数据集上训练，该工作还展示了实现可迁移 Langevin Flow Maps 的路径。
正文
Abstract: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.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.05998 [cs.LG] |
| (or arXiv:2610.05998v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.05998 arXiv-issued DOI via DataCite |
Submission history
From: Sam McCallum [view email]
[v1]
Mon, 5 Oct 2026 08:51:38 UTC (1,336 KB)
[v2]
Wed, 14 Oct 2026 09:18:28 UTC (1,336 KB)
来源：arXiv：cs.LG · arxiv.org