A co-trained multifidelity mixture-of-experts MLIP partitions simulations into high- and low-capacity regions, maintains exact energy conservation and bulk modulus alignment, and runs more than twice as fast as a single high-fidelity model on a Pt+CO system.
Active learning of reactive bayesian force fields applied to heterogeneous catalysis dynamics of h/pt.Nature Communications, 13(1):5183
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.comp-ph 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Mixture of Experts Framework in Machine Learning Interatomic Potentials for Atomistic Simulations
A co-trained multifidelity mixture-of-experts MLIP partitions simulations into high- and low-capacity regions, maintains exact energy conservation and bulk modulus alignment, and runs more than twice as fast as a single high-fidelity model on a Pt+CO system.