Miguel A. Caro

Cluster-based Structural Similarity for Dataset Visualization and Data Selection for Machine Learning Interatomic Potentials

Machine learning interatomic potentials (MLIPs) are essential components for accelerating simulation-driven materials design. Data-efficient MLIP training relies on data-selection strategies that maximize structural diversity while limiting computationally expensive first-principles calculations. A key challenge in suc...

Exploring the con fi guration space of elemental carbon with empirical and machine learned interatomic potentials

Artificial Intelligence for Advanced Functional Materials: Progress and Emerging Frontiers

This Perspective examines how recent advances in data‐driven modeling, high‐performance simulation, and autonomous experimentation are converging to accelerate the discovery of functional materials for next‐generation technologies—from energy storage and biomedicine to nanoelectronics and quantum devices.