Comparing the Latent Features of Universal Machine‐Learning Interatomic Potentials

The past few years have seen the development of “universal” machine‐learning interatomic potentials (uMLIPs) capable of approximating the ground‐state potential energy surface across a wide range of chemical structures and compositions with reasonable accuracy. While these models differ in the archi...

Full description

Bibliographic Details

Published in:	Advanced Intelligent Systems
Main Authors:	Sofiia Chorna, Davide Tisi, Cesare Malosso, Wei Bin How, Michele Ceriotti, Sanggyu Chong
Format:	Article
Language:	English
Published:	Wiley 2026-05-01
Subjects:	atomistic machine learning latent feature analysis universal machine‐learning interatomic potentials
Online Access:	https://doi.org/10.1002/aisy.202501497