Geometry-diverse fine-tuning, not single-geometry adaptation, best restores accuracy of foundation interatomic potentials on ZrO2 nanostructures.
For MACE, fine-tuning gives the lowest mean relative surface-energy error, ap- proximately 3.08%, compared with 3.33% for training from scratch and 16.14% for zero-shot inference
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cond-mat.mtrl-sci 1years
2026 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Cross-Geometry Transferability Assessment of Universal Machine Learning Interatomic Potentials: From Bulk Materials to Atomic Nanowires
Geometry-diverse fine-tuning, not single-geometry adaptation, best restores accuracy of foundation interatomic potentials on ZrO2 nanostructures.