The paper, "Predicting Interface Structure Using the Minima Hopping Method with a Machine Learning Interatomic Potential," introduces a framework that combines the minima hopping method (MHM) with the Allegro machine-learning interatomic potential (MLIP) to accurately predict atomic-scale interface structures. The approach successfully identifies low-energy grain boundary configurations and demonstrates strong agreement with experimental observations, providing a powerful strategy for bridging atomistic simulations and experimental characterization. Congratulations to Chang-Ti and all the co-authors on this outstanding achievement!

https://www.nature.com/articles/s41524-026-02214-7