Constrained Diffusion for Accelerated Structure Relaxation of Inorganic Solids with Point Defects

Jingyi Cui, Jacob K Christopher, Ankita Biswas, Prasanna V. Balachandran, Ferdinando Fioretto

Keywords: Diffusion Models, Constrained Generative Modeling, Point Defect Simulation, Thermoelectric Materials, Physics-informed Machine Learning

TL;DR: [Short paper] We address the problem of simulating point defects in Bi₂Te₃ by introducing a primal–dual algorithm for constrained generative diffusion modeling, achieving state-of-the-art physically realistic structures.

Abstract:

Point defects affect material properties by altering electronic states and modifying local bonding environments. However, high-throughput first-principles simulations of point defects are costly due to large simulation cells and complex energy landscapes.
To this end, we propose a generative framework for simulating point defects, overcoming the limits of costly first-principles simulators.
By leveraging a primal-dual algorithm, we introduce a constraint-aware diffusion model which outperforms existing constrained diffusion approaches in this domain. Across six defect configuration settings for $Bi_2Te_3$, the proposed approach provides state-of-the-art performance generating physically grounded structures.

Submission Track: Paper Track (Short Paper)

Submission Category: AI-Guided Design

Institution Location: Virginia, United State of America

AI4Mat RLSF: Yes

Submission Number: 128