A Hamiltonian-predicting neural network, QHFlow2, reaches NequIP-level force accuracy and 20× lower energy errors than MLIPs when energies and forces are computed directly from its predicted Hamiltonians.
Recent advances in machine learning- assisted multiscale design of energy materials
1 Pith paper cite this work, alongside 153 external citations. Polarity classification is still indexing.
1
Pith paper citing it
153
external citations · OpenAlex
fields
physics.comp-ph 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Machine Learning Hamiltonians are Accurate Energy-Force Predictors
A Hamiltonian-predicting neural network, QHFlow2, reaches NequIP-level force accuracy and 20× lower energy errors than MLIPs when energies and forces are computed directly from its predicted Hamiltonians.