5 papers
Inverse design of superconductors and semiconductors with differentiable foundation models
Cristóbal Méndez, Justin Tahmassebpur, Tomás A. Arias
Designing a crystal for a target property requires choosing its elements, stoichiometry, and atomic structure together, yet gradients exist only for the continuous structural varia…
Hereditary Effective Atom Theory for Large-Scale Atomic Structure Prediction
Justin Tahmassebpur, Chia-Hao Lee, Cristóbal Méndez +6
Predicting the atomic structure of large systems requires simultaneous exploration of atomic positions, species, and, generally, the number of atoms. The combinatorial growth of po…
Neural networks become centroid classifiers when trained on heavily corrupted inputs
Justin Tahmassebpur, Asadullah Bhuiyan, Hyejin Kim +1
Learning from imperfect data is a central theme in machine learning, connecting practical questions of robustness to fundamental questions of learnability. Here we examine attribut…
A geometric basis for materials families in inorganic solids
Justin Tahmassebpur, Sarvesh Chaudhari, Cristóbal Méndez +6
The thermodynamic stability of inorganic solids spans a vast compositional space, yet materials scientists have long organized their intuition around a manageable number of materia…
Effective Atom Theory: Gradient-Driven Materials Design
Justin Tahmassebpur, Brandon Li, Cristobál Méndez +4
We introduce Effective Atom Theory (EAT), which embeds discrete atomic identities into a continuous differentiable space. During optimization, sites pass through temporary effectiv…