3 papers
physics.chem-ph2026
Diagnosing Latent Energy Decomposition in Machine-Learning Interatomic Potentials via Interacting Quantum Atoms
Kohei Shimamura, Ken-ichi Nomura
Machine-learning interatomic potentials (MLIPs) can reproduce potential energies and forces accurately, but their internal energy allocation is often difficult to interpret. E3D-IQ…
cond-mat.mtrl-sci2025
Beyond Scaling: Chemical Intuition as Emergent Ability of Universal Machine Learning Interatomic Potentials
Shinnosuke Hattori, Kohei Shimamura, Aiichiro Nakano +3
Machine Learning Interatomic Potentials (MLIPs) have successfully demonstrated scaling behavior, i.e. the power-law improvement in training performance, however the emergence of no…
cond-mat.mtrl-sci2025
Allegro-FM: Towards Equivariant Foundation Model for Exascale Molecular Dynamics Simulations
Ken-ichi Nomura, Shinnosuke Hattori, Satoshi Ohmura +6
We present a foundation model for exascale molecular dynamics simulations by leveraging an E(3) equivariant network architecture (Allegro) and a set of large-scale organic and inor…