Showing cond-mat.mtrl-sciShow all
2 papers · 1 filter
cond-mat.mtrl-sci2026
Data-Efficient Construction of Material-Specific Machine-Learning Interatomic Potentials from Ab Initio Molecular Dynamics Trajectories
Jonas Hänseroth, Christian Dreßler
Pretrained machine-learning interatomic potentials, so-called universal or foundation models offer an appealing starting point for atomistic simulations, but their accuracy for mat…
cond-mat.mtrl-sci2026
Universal Interatomic Potentials as Configuration-Space Generators for One-Shot and Iterative Fine-Tuning of Ab Initio-Accurate Material-Specific Models
Jonas Hänseroth, Aaron Flötotto, Christian Dreßler
Universal machine-learning interatomic potentials (MLIPs) are rapidly becoming general-purpose tools for atomistic simulation, but their role in quantitative materials modeling whe…