"In this talk, I will discuss recent developments in AI-based interatomic potentials, which have improved our ability to model atomic interactions by effectively partitioning energy at each atomic site. While these AI potentials have made significant progress in predicting material properties, challenges remain—particularly in addressing elevated temperature effects and long-range interactions, both of which are crucial in condensed matter systems.
I will also highlight the emerging use of generative AI models to predict atomic trajectories, offering a potential paradigm shift away from traditional force-field methods. Additionally, I will explore the synergy between Variational Quantum Eigensolver (VQE) and Quantum Machine Learning (QML) in modeling the energetics during surface dynamics. These methods could provide new insights into processes such as thin-film deposition and barrier formation, which are essential for technologies like superconducting qubits."