Langevin Flow Maps: Efficient Molecular Dynamics and Transition Path Sampling

Sam McCallum; Niklas Rindtorff; Alexander Tong; James Foster

cs.LGOct 5, 2026

Langevin Flow Maps: Efficient Molecular Dynamics and Transition Path Sampling

Authors: Sam McCallum, Niklas Rindtorff, Alexander Tong, James Foster

Organizations: University of Bath · AITHYRA

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.

Explore similar work

Learning Hamiltonian Flow Maps: Mean Flow Consistency for Large-Timestep Molecular Dynamics
Jan 29, 2026Winfried Ripken, Michael Plainer, Gregor Lied +5Invertible Flows Hamiltonian
Technical University Berlin · BIFOLD · Free University of Berlin +6
Langevin-Informed Transfer Learning: Replacing Target Samples by Black-Box Feedback
Oct 1, 2026Vladimir R. Kostic, Karim Lounici, Hélène Halconruy +3Langevin Dynamics Transfer Learning
CSML, Istituto Italiano di Tecnologia · University of Novi Sad · CMAP-Ecole Polytechnique +5
Speculative Sampling For Faster Molecular Dynamics
Jun 1, 2026Arthur Kosmala, Stephan Günnemann, Meng Gao +1Molecular Dynamics Langevin Dynamics
1FAIR at Meta · School of Computation, Information & Technology, Technical University of Munich · 3Munich Data Science Institute +1

Jan 29, 2026, cs.LGJ/K move · Enter open · S save

Learning Hamiltonian Flow Maps: Mean Flow Consistency for Large-Timestep Molecular Dynamics

Winfried Ripken, Michael Plainer, Gregor Lied, Thorben Frank+4

Technical University Berlin · BIFOLD · Free University of Berlin+6

Invertible Flows Hamiltonian Phase Space Molecular Dynamics Meanflow

Open paper AskPDF arXiv

Simulating the long-time evolution of Hamiltonian systems is limited by the small timesteps required for stable numerical integration. To overcome this constraint, we introduce a framework to learn Hamiltonian Flow Maps by predicting the mean phase-space evolution over a chosen time span, enabling stable large-timestep updates far beyond the stability limits of classical integrators. To this end, we impose a Mean Flow consistency condition for time-averaged Hamiltonian dynamics. Unlike prior approaches, this allows training on independent phase-space samples without access to future states, avoiding expensive trajectory generation. Validated across diverse Hamiltonian systems, our method in particular improves upon molecular dynamics simulations using machine-learned force fields (MLFF). Our models maintain comparable training and inference cost, but support significantly larger integration timesteps while trained directly on widely-available trajectory-free MLFF datasets.

Abstract

Explore similar work

Learning Hamiltonian Flow Maps: Mean Flow Consistency for Large-Timestep Molecular Dynamics

Langevin-Informed Transfer Learning: Replacing Target Samples by Black-Box Feedback

Speculative Sampling For Faster Molecular Dynamics