4 papers
Neural-Network Solutions to Real-Space Charge Density and Generalization
Yuxuan Zeng, Tong Xie, Taoyuze Lv +1
The Hohenberg-Kohn theorem establishes that, in principle, the ground state (GS) charge density contains all GS information of a many-electron system, such that all GS observables…
Data-Efficient Adaptation of DPA-4 Force Fields to DFT+U Energetics: A Case Study in NiO
Fengyu Xie, Peiheng Jiang, Zhicheng Zhong
Foundation machine-learned force fields (MLFFs) are often pretrained on broad materials datasets whose electronic-structure conventions may not reproduce the phase energetics requi…
AtomWorld: A Benchmark for Evaluating Spatial Reasoning in Large Language Models on Crystalline Materials
Taoyuze Lv, Alexander Chen, Fengyu Xie +7
Large language models (LLMs) have shown promising potential in scientific research, enabling tasks ranging from knowledge retrieval to property prediction. Existing science benchma…
EAC-Net: Predicting real-space charge density via equivariant atomic contributions
Xuejian Qin, Taoyuze Lv, Zhicheng Zhong
Charge density is central to density functional theory (DFT), as it fully defines the ground-state properties of a material system. Obtaining it with high accuracy is a computation…