Preprint
Aug 2026
Cartesian tensor equivariant machine-learning force field for spin-dependent atomistic simulations
HotPP-Spin is introduced, a spin-dependent extension of HotPP for magnetic machine learning interatomic potentials, built on Cartesian tensor equivariant message passing, establishing Cartesian tensor message passing as a general route for connecting first-principles magnetic energetics with large-scale atomistic simul...
Jun-Jie Wang, Yi-Jie Zhu, Zhong-Wei Zhang et al.
· 0 citations