2 papers
physics.chem-ph2026
Expanding Universal Machine Learning Interatomic Potentials to 97 Elements Towards Nuclear Applications
Naoya Kuroda, Kenji Ishihara, Tomoya Shiota +1
Machine learning interatomic potentials (MLIPs) evaluate potential energy surfaces orders of magnitude faster while maintaining accuracy comparable to first-principles calculations…
physics.chem-ph2024
Taming Multi-Domain, -Fidelity Data: Towards Foundation Models for Atomistic Scale Simulations
Tomoya Shiota, Kenji Ishihara, Tuan Minh Do +2
Machine learning interatomic potentials (MLIPs) are changing atomistic simulations in the field of chemistry and materials science. However, constructing a single universal MLIP th…