3 papers
physics.comp-ph2026
NEPMaker: Active learning of neuroevolution machine learning potential for large cells
Junjie Wang, Shuning Pan, Haoting Zhang +4
Machine learning potentials (MLPs) achieve near first-principles accuracy but often fail for atomic environments outside the training distribution. Active learning can mitigate thi…
cond-mat.mtrl-sci2026
GPUTB-2:An efficient E(3) network method for learning high-precision orthogonal Hamiltonian
Yunlong Wang, Zhixin Liang, Chi Ding +5
Although equivariant neural networks have become a cornerstone for learning electronic Hamiltonians, the intrinsic non-orthogonality of linear combinations of atomic orbitals (LCAO…
cond-mat.mtrl-sci2025
GPUTB: Efficient Machine Learning Tight-Binding Method for Large-Scale Electronic Properties Calculations
Yunlong Wang, Zhixin Liang, Chi Ding +5
The high computational cost of ab-initio methods limits their application in predicting electronic properties at the device scale. Therefore, an efficient method is needed to map t…