Tag
Researchers from MIT, University of Warwick, and NVIDIA introduce Stein Kernelized Molecular Dynamics (SKMD), an enhanced sampling method that uses interacting particle dynamics to acquire informative training configurations for active learning and fine-tuning of machine learning interatomic potentials (MLIPs). SKMD is a stochastic variant of Stein variational gradient descent adapted for molecular dynamics, preserving the Boltzmann distribution while achieving higher model accuracy in fewer training iterations compared to baselines.
EvoMD-LLM reformulates reactive molecular dynamics trajectories as symbolic temporal sequences, enabling LLMs to model species evolution over time through fine-tuning and temporal scaffolding, achieving up to 66.14% accuracy and interpretable predictions.
This paper introduces a Hessian matching framework for machine-learned coarse-grained molecular dynamics that augments force matching with stochastic Hessian-vector product matching, instilling second-order curvature information into CG potentials. The method achieves up to 85% reduction in Kullback-Leibler divergence on slow-mode metrics for fast-folding proteins.