works on

From the 1 of 7 linked papers with an AI index.

activity
20242026
collaborators

7 papers

cond-mat.mtrl-sci2026

PASS: Perturbation augmented space group structure sampling for transferable Fe-O machine learning interatomic potential

Zixiong Wei, Fei Shuang, Poulumi Dey

The paper introduces the PASS (Perturbation Augmented Space group structure Sampling) method to create a diverse first‑principles dataset for training a transferable machine‑learni…

cond-mat.mtrl-sci2025

Model Accuracy and Data Heterogeneity Shape Uncertainty Quantification in Machine Learning Interatomic Potentials

Fei Shuang, Zixiong Wei, Kai Liu +2

Machine learning interatomic potentials (MLIPs) enable accurate atomistic modelling, but reliable uncertainty quantification (UQ) remains elusive. In this study, we investigate two…

cond-mat.mtrl-sci2025

Heterogeneous Ensemble Enables a Universal Uncertainty Metric for Atomistic Foundation Models

Kai Liu, Zixiong Wei, Wei Gao +3

Universal machine learning interatomic potentials (uMLIPs) are reshaping atomistic simulation as foundation models, delivering near \textit{ab initio} accuracy at a fraction of the…

cond-mat.mtrl-sci2025

Kinetics of Vacancy-Assisted Reversible Phase Transition in Monolayer MoTe

Fei Shuang, Daniel Ocampo, Reza Namakian +3

We investigate the kinetics of phase transition between the 2H and 1T phases in monolayer MoTe using atomistic simulations based on a machine learning interatomic pote…

cond-mat.mtrl-sci2025

Universal machine learning interatomic potentials poised to supplant DFT in modeling general defects in metals and random alloys

Fei Shuang, Zixiong Wei, Kai Liu +2

Recent advances in machine learning, combined with the generation of extensive density functional theory (DFT) datasets, have enabled the development of universal machine learning…

cond-mat.mtrl-sci2025

Modeling Extensive Defects in Metals through Classical Potential-Guided Sampling and Automated Configuration Reconstruction

Fei Shuang, Kai Liu, Yucheng Ji +3

Extended defects such as dislocation networks and general grain boundaries are ubiquitous in metals, and accurately modeling these extensive defects is crucial for understanding th…