arXiv subjects

Jaesun Kim

Publications and source records attributed to Jaesun Kim.

7 recordsLinked to original sources

arXiv2026

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

Computational materials science has traditionally delegated algorithmic tasks to computers while leaving scientific judgments to humans. We argue that recent LLM-based agent harnesses enable an emerging form of scientific software, agentic programs, that combine deterministic algorithms with bounded LLM-based judgment, task-specific verification, episodic maturation, and complete delegation in production. We illustrate this concept with DeMARS, an agentic program for constructing atomistic models from experimentally measured disordered crystal structures.

cond-mat.mtrl-sci↗

arXiv2026

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

Alloys inevitably contain interphase boundaries, whose energetics govern nucleation processes and precipitate morphology. In Cu-Ni-Si alloys, Mn addition markedly changes grain boundary (GB) precipitation behavior. While GB precipitation of stable Ni$_2$Si in Mn-free alloys is associated with degraded mechanical properties, Mn addition instead promotes film-shaped Mn$_6$Ni$_{16}$Si$_7$ (G-phase) precipitation, which is correlated improved mechanical properties. However, the atomic origin of the contrasting GB phase selection and morphology remains unclear. Here we perform machine-learning interatomic potential (MLIP) calculations to investigate the effect of interphase-boundary atomic structure on GB precipitates in Cu-Ni-Si alloys with and without Mn. The MLIP calculations reliably reproduce DFT-level energetics for interfacial bonding and microstructural configurations, and further predict that Mn addition favors GB precipitation of Mn$_6$Ni$_{16}$Si$_7$ rather than Ni$_2$Si. Experimentally, Mn-free alloys are observed to exhibit irregularly-shaped Ni$_2$Si precipitates with open-boundary-like Cu/Ni$_2$Si interfaces, whereas Mn-added alloys exhibit film-like G-phase at GBs. Large-scale atomistic interface calculations reveal that the coherent interface structure between Cu and Ni$_2$Si favors the formation of plate-like strained Ni$_2$Si precipitates in the matrix. Upon coarsening and stress release, an out-of-phase coherent-like interface can form at GBs, generating a local repulsive region that gives rise to surface-like open-boundary structures and explains the irregular morphology of GB stable Ni$_2$Si precipitates. In contrast, Cu/Mn$_6$Ni$_{16}$Si$_7$ interfaces remain predominantly incoherent with moderate boundary energies and no pronounced repulsive regime, thereby stabilizing continuous interfacial contact and explaining film-shaped GB precipitation.

cond-mat.mtrl-sci↗

arXiv2026

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

We introduce a lightweight universal machine-learning interatomic potential (uMLIP), SevenNet-Nano, based on the graph neural network architecture SevenNet and enabled by a knowledge-distillation framework. The model inherits the broad generalization capability of a large multi-task foundation model, SevenNet-Omni, trained on diverse materials datasets across chemical, configurational, and computational spaces. By learning chemical representations from high-quality inference data generated by the teacher model within a unified computational framework, SevenNet-Nano achieves high accuracy and strong transferability despite its compact architecture. The model also accurately captures a wide range of interatomic interactions, enabling reliable simulations under both equilibrium and extreme conditions, including plasma etching of SiO$_2$. Comprehensive benchmarks on static and dynamical properties--such as Li-ion diffusion and liquid densities--demonstrate its broad applicability with minimal fine-tuning. Importantly, SevenNet-Nano significantly reduces computational cost, achieving over an order-of-magnitude speedup and enabling large-scale atomistic simulations involving thousands of atoms.

cond-mat.mtrl-sci↗

arXiv2025

Optimizing Cross-Domain Transfer for Universal Machine Learning Interatomic Potentials

Accurate yet transferable machine-learning interatomic potentials (MLIPs) are essential for accelerating materials and chemical discovery. However, most universal MLIPs overfit to narrow datasets or computational protocols, limiting their reliability across chemical and functional domains. We introduce a transferable multi-domain training strategy that jointly optimizes universal and task-specific parameters through selective regularization, coupled with a domain-bridging set (DBS) that aligns potential-energy surfaces across datasets. Systematic ablation experiments show that small DBS fractions (0.1%) and targeted regularization synergistically enhance out-of-distribution generalization while preserving in-domain fidelity. Trained on fifteen open databases spanning molecules, crystals, and surfaces, our model, SevenNet-Omni, achieves state-of-the-art cross-domain accuracy, including adsorption-energy errors below 0.06 eV on metallic surfaces and 0.1 eV on metal-organic frameworks. Despite containing only 0.5% r$^2$SCAN data, SevenNet-Omni reproduces high-fidelity r$^2$SCAN energetics, demonstrating effective cross-functional transfer from large PBE datasets. This framework offers a scalable route toward universal, transferable MLIPs that bridge quantum-mechanical fidelities and chemical domains.

cond-mat.mtrl-sci↗

arXiv2025

Unveiling defect motifs in amorphous GeSe using machine learning interatomic potentials

Ovonic threshold switching (OTS) selectors play a critical role in non-volatile memory devices because of their nonlinear electrical behavior and polarity-dependent threshold voltages. However, the atomic-scale origins of the defect states responsible for these properties are not yet fully understood. In this study, we use molecular dynamics simulations accelerated by machine-learning interatomic potentials to investigate defects in amorphous GeSe. We begin by benchmarking several potential architectures-including descriptor-based models and graph neural network (GNN) models-and show that faithfully representing amorphous GeSe requires capturing higher-order interactions (at least four-body correlations) and medium-range structural order. We find that GNN architectures with multiple interaction layers successfully capture these correlations and structural motifs, preventing the spurious defects that less expressive models introduce. With our optimized GNN potential, we examine twenty independent 960-atom amorphous GeSe structures and identify two distinct defect motifs: aligned Ge chains, which give rise to defect states near the conduction band, and overcoordinated Ge chains, which produce defect states near the valence band. We further correlate these electronic defect levels with specific structural features-namely, the average alignment of bond angles in the aligned chains and the degree of local Peierls distortion around overcoordinated Ge atoms. These findings provide a theoretical framework for interpreting experimental observations and deepen our understanding of defect-driven OTS phenomena in amorphous GeSe.

cond-mat.mtrl-sci↗

arXiv2024

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

Machine learning interatomic potentials (MLIPs) are used to estimate potential energy surfaces (PES) from ab initio calculations, providing near quantum-level accuracy with reduced computational costs. However, the high cost of assembling high-fidelity databases hampers the application of MLIPs to systems that require high chemical accuracy. Utilizing an equivariant graph neural network, we present an MLIP framework that trains on multi-fidelity databases simultaneously. This approach enables the accurate learning of high-fidelity PES with minimal high-fidelity data. We test this framework on the Li$_6$PS$_5$Cl and In$_x$Ga$_{1-x}$N systems. The computational results indicate that geometric and compositional spaces not covered by the high-fidelity meta-gradient generalized approximation (meta-GGA) database can be effectively inferred from low-fidelity GGA data, thus enhancing accuracy and molecular dynamics stability. We also develop a general-purpose MLIP that utilizes both GGA and meta-GGA data from the Materials Project, significantly enhancing MLIP performance for high-accuracy tasks such as predicting energies above hull for crystals in general. Furthermore, we demonstrate that the present multi-fidelity learning is more effective than transfer learning or $\Delta$-learning an d that it can also be applied to learn higher-fidelity up to the coupled-cluster level. We believe this methodology holds promise for creating highly accurate bespoke or universal MLIPs by effectively expanding the high-fidelity dataset.

cond-mat.mtrl-sci↗

arXiv2024

Scalable Parallel Algorithm for Graph Neural Network Interatomic Potentials in Molecular Dynamics Simulations

Message-passing graph neural network interatomic potentials (GNN-IPs), particularly those with equivariant representations such as NequIP, are attracting significant attention due to their data efficiency and high accuracy. However, parallelizing GNN-IPs poses challenges because multiple message-passing layers complicate data communication within the spatial decomposition method, which is preferred by many molecular dynamics (MD) packages. In this article, we propose an efficient parallelization scheme compatible with GNN-IPs and develop a package, SevenNet (Scalable EquiVariance-Enabled Neural NETwork), based on the NequIP architecture. For MD simulations, SevenNet interfaces with the LAMMPS package. Through benchmark tests on a 32-GPU cluster with examples of SiO$_2$, SevenNet achieves over 80% parallel efficiency in weak-scaling scenarios and exhibits nearly ideal strong-scaling performance as long as GPUs are fully utilized. However, the strong-scaling performance significantly declines with suboptimal GPU utilization, particularly affecting parallel efficiency in cases involving lightweight models or simulations with small numbers of atoms. We also pre-train SevenNet with a vast dataset from the Materials Project (dubbed `SevenNet-0') and assess its performance on generating amorphous Si$_3$N$_4$ containing more than 100,000 atoms. By developing scalable GNN-IPs, this work aims to bridge the gap between advanced machine learning models and large-scale MD simulations, offering researchers a powerful tool to explore complex material systems with high accuracy and efficiency.

cond-mat.mtrl-sci↗