Zero-shot r2SCAN energies from the PET-OMATPES MLIP cut GGA formation-energy errors by >40%, and delta-learning on the MLIP's latent features pushes the MAE below 50 meV/atom.
de Miranda Nascimento, F
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.mtrl-sci 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Correcting DFT formation energies towards experimental accuracy using foundational MLIPs and latent-feature delta-learning
Zero-shot r2SCAN energies from the PET-OMATPES MLIP cut GGA formation-energy errors by >40%, and delta-learning on the MLIP's latent features pushes the MAE below 50 meV/atom.