Gregor Lied

Master’s student and student researcher in the Machine Learning Group at TU Berlin, supervised by Stefan Chmiela in Klaus-Robert Müller’s group. His work focuses on machine learning for molecular simulation, including generative models, graph neural networks, and ML for the physical sciences.

Hamiltonian Flow Maps Learn Larger Molecular Dynamics Steps Without Trajectories

Michael Plainer, Winfried Ripken and Gregor Lied argue that generative models can attack molecular dynamics’ central bottleneck: the gap between femtosecond integration steps and biological processes that unfold many orders of magnitude later. In the Microsoft Research seminar, they separate the problem by timescale, using diffusion models to sample equilibrium Boltzmann states and extract force information, while proposing Hamiltonian flow maps for the intermediate regime where simulations need large, stable steps without training on expensive future-state trajectories.

Microsoft ResearchMay 26, 202618 min read