Dyna-Mat-v1.0 benchmarks 15 foundation MLIPs on finite-T MD observables, finding average force-error correlation with RDF/VDOS but systematic pressure failures and near-Pareto optimality of latest cross-trained models.
Choudhary , author D
1 Pith paper cite this work, alongside 49 external citations. Polarity classification is still indexing.
1
Pith paper citing it
49
external citations · OpenAlex
fields
cond-mat.mtrl-sci 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dyna-Mat: End-to-end benchmarking of foundation machine learning interatomic potentials in finite-temperature ensembles
Dyna-Mat-v1.0 benchmarks 15 foundation MLIPs on finite-T MD observables, finding average force-error correlation with RDF/VDOS but systematic pressure failures and near-Pareto optimality of latest cross-trained models.