activity
20242026
most citedOptimizing Cross-Domain Transfer for Universal Machine Learning Interatomic Potentials

3 citations · 4 across the 5 of their papers we have counts for

collaborators
Showing cond-mat.mtrl-sciShow all

7 papers · 1 filter

cond-mat.mtrl-sci2026

Agentic programs: an emerging form of scientific software in computational materials science

Yunsung Lim, Haekwan Jeon, Jaesun Kim +2

Computational materials science has traditionally delegated algorithmic tasks to computers while leaving scientific judgments to humans. We argue that recent LLM-based agent harnes…

cond-mat.mtrl-sci2026

Precipitate phase selection and grain boundary morphology in Cu-Ni-Si-Mn alloys: A machine-learning interatomic potential study

Aadil Fayaz Wani, Il-Seok Jeong, Haekwan Jeon +6

Alloys inevitably contain interphase boundaries, whose energetics govern nucleation processes and precipitate morphology. In Cu-Ni-Si alloys, Mn addition markedly changes grain bou…

cond-mat.mtrl-sci20261 cited

A Lightweight Universal Machine-Learning Interatomic Potential via Knowledge Distillation for Scalable Atomistic Simulations

Sangmin Oh, Jinmu You, Jaesun Kim +4

We introduce a lightweight universal machine-learning interatomic potential (uMLIP), SevenNet-Nano, based on the graph neural network architecture SevenNet and enabled by a knowled…

cond-mat.mtrl-sci20253 cited

Optimizing Cross-Domain Transfer for Universal Machine Learning Interatomic Potentials

Jaesun Kim, Jinmu You, Yutack Park +11

Accurate yet transferable machine-learning interatomic potentials (MLIPs) are essential for accelerating materials and chemical discovery. However, most universal MLIPs overfit to…

cond-mat.mtrl-sci2025

Unveiling defect motifs in amorphous GeSe using machine learning interatomic potentials

Minseok Moon, Seungwoo Hwang, Jaesun Kim +3

Ovonic threshold switching (OTS) selectors play a critical role in non-volatile memory devices because of their nonlinear electrical behavior and polarity-dependent threshold volta…

cond-mat.mtrl-sci2024

Data-efficient multi-fidelity training for high-fidelity machine learning interatomic potentials

Jaesun Kim, Jisu Kim, Jaehoon Kim +4

Machine learning interatomic potentials (MLIPs) are used to estimate potential energy surfaces (PES) from ab initio calculations, providing near quantum-level accuracy with reduced…