3 papers
cs.LG2026
Feature Learning Dynamics in Infinite-Depth Neural Networks
Zihan Yao, Ruoyu Wu, Tianxiang Gao
Deep neural networks have achieved remarkable success in practice, yet a mechanistic understanding of how features evolve during training remains incomplete, especially in the larg…
cs.LG2025
Data-Efficient Machine Learning Potentials via Difference Vectors Based on Local Atomic Environments
Xuqiang Shao, Yuqi Zhang, Di Zhang +10
Constructing efficient and diverse datasets is essential for the development of accurate machine learning potentials (MLPs) in atomistic simulations. However, existing approaches o…
cond-mat.mtrl-sci2025
Universal Catalyst Design Framework for Electrochemical Hydrogen Peroxide Synthesis Facilitated by Local Atomic Environment Descriptors
Zhijian Liu, Yan Liu, Bingqian Zhang +10
Developing a universal and precise design framework is crucial to search high-performance catalysts, but it remains a giant challenge due to the diverse structures and sites across…