A machine learning interatomic potential trained only on total energies and forces learns per-bond energy components that match experimental bond dissociation energies, an ability the authors call emergent.
Scaling the leading accuracy of deep equivariant models to biomolecular simulations of realistic size
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cond-mat.mtrl-sci 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Beyond Scaling: Chemical Intuition as Emergent Ability of Universal Machine Learning Interatomic Potentials
A machine learning interatomic potential trained only on total energies and forces learns per-bond energy components that match experimental bond dissociation energies, an ability the authors call emergent.