works on
amorphous structure generation 1density prediction 1machine learning interatomic potentials 1melt-quench simulations 1validation protocols 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cond-mat.mtrl-sci2026

Melt-Quench Failures and Practical Solutions for Universal Machine-Learning Interatomic Potentials in Amorphous Structure Generation

Shuwei Li, Yuqi An, Xingyu Guo +2

The paper investigates why universal machine‑learning interatomic potentials (uMLIPs) often produce unrealistically low densities when used for melt‑quench simulations of amorphous…