Towards A Universally Transferable Acceleration Method for Density Functional Theory
Zhe Liu, Yuyan Ni, Zhichen Pu, Qiming Sun, Siyuan Liu, Wen Yan
The Fourteenth International Conference on Learning Representations (ICLR 2026)
TL;DR:
We propose using Graph Neural Networks to learn electron density. This approach exhibits superior
transferability in various aspects. A follow-up work is currently in preparation.
Nonadiabatic Dynamics with Constrained Nuclear-Electronic Orbital Theory
Zhe Liu, Zehua Chen, Yang Yang
The Journal of Physical Chemistry Letters (J. Phys. Chem. Lett.)
TL;DR:
We developed a new nonadiabatic dynamics method that efficiently incorporates nuclear quantum
effects.