BoostMD accelerates MLFF molecular dynamics by predicting energy changes from previous-step node features and positional displacements, reporting 8x speedup and matching the reference model's sampled free energy surface on an unseen dipeptide.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.chem-ph 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
BoostMD: Accelerating molecular sampling by leveraging ML force field features from previous time-steps
BoostMD accelerates MLFF molecular dynamics by predicting energy changes from previous-step node features and positional displacements, reporting 8x speedup and matching the reference model's sampled free energy surface on an unseen dipeptide.