3 papers
cond-mat.mtrl-sci2026
AccelNet: Exact backward-compatible acceleration of polynomial angular descriptors through Cartesian moment factorization
Yuki Nagai
We present AccelNet, an exact, backward-compatible method for accelerating existing trained aenet and n2p2 neural-network potentials without retraining. For angular terms with sepa…
cond-mat.mtrl-sci2026
Target-Distribution-Guided Cross-Functional Fine-Tuning of Machine-Learning Interatomic Potentials
Yuki Nagai, Bo Thomsen, Motoyuki Shiga
Cross-functional fine-tuning of machine-learning interatomic potentials (MLIPs) is often treated as a relabeling problem, where configurations generated at one density-functional l…
physics.chem-ph2024
Self-learning path integral hybrid Monte Carlo with mixed ab initio and machine learning potentials for modeling nuclear quantum effects in water
Bo Thomsen, Yuki Nagai, Keita Kobayashi +2
The introduction of machine learned potentials (MLPs) has greatly expanded the space available for studying Nuclear Quantum Effects computationally with ab initio path integral (PI…