SKMD adapts Stein variational gradient descent into molecular dynamics with asynchronous updates and global atomic descriptor kernels to acquire non-redundant training configurations while preserving the Boltzmann distribution, yielding higher MLIP accuracy with fewer samples than baselines.
Well-Tempered Metadynamics: A Smoothly Converging and Tunable Free-Energy Method
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
DeltaDiff is a physics-guided inference method that predicts mutant protein structures from a baseline diffusion model without retraining, tested on three systems with nonlocal changes.
A committor-guided Milestoning (CoM) algorithm using neural-network ansatz and short trajectories for efficient prediction of mean first passage times in biomolecular systems.
citing papers explorer
-
Stein Kernelized Molecular Dynamics for Active Learning of Interatomic Potentials
SKMD adapts Stein variational gradient descent into molecular dynamics with asynchronous updates and global atomic descriptor kernels to acquire non-redundant training configurations while preserving the Boltzmann distribution, yielding higher MLIP accuracy with fewer samples than baselines.
-
DeltaDiff: Training-Free, Physics-Guided Machine Learning for Predicting Mutant Protein Structures
DeltaDiff is a physics-guided inference method that predicts mutant protein structures from a baseline diffusion model without retraining, tested on three systems with nonlocal changes.
-
Fast and accurate committor estimation for kinetics simulations
A committor-guided Milestoning (CoM) algorithm using neural-network ansatz and short trajectories for efficient prediction of mean first passage times in biomolecular systems.