4 papers
Meta-LegNet: A Transferable and Interpretable Framework for Surface Adsorption Prediction via Self-Defined Adsorption-Environment Learning
Yifan Li, Arravind Subramanian, Xiaoqing Liu +3
A central challenge in computational catalysis is the identification of low-energy and chemically plausible adsorption configurations, as these directly affect adsorption energies,…
Scalable Crystal Structure Relaxation Using an Iteration-Free Deep Generative Model with Uncertainty Quantification
Ziduo Yang, Yi-Ming Zhao, Xian Wang +6
In computational molecular and materials science, determining equilibrium structures is the crucial first step for accurate subsequent property calculations. However, the recent di…
Local environment-based machine learning for molecular adsorption energy prediction
Yifan Li, Yihan Wu, Yuhang Han +4
Most machine learning (ML) models in Materials Science are developed by global geometric features, often falling short in describing localized characteristics, like molecular adsor…
Lightweight equivariant model for efficient machine learning interatomic potentials
Ziduo Yang, Xian Wang, Yifan Li +3
In modern computational materials science, deep learning has shown the capability to predict interatomic potentials, thereby supporting and accelerating conventional simulations. H…