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

TL;DR

This paper introduces a constraint-aware diffusion model that accelerates the simulation of point defects in inorganic solids, providing more efficient and accurate structure relaxation compared to traditional first-principles methods.

Contribution

It presents a novel generative framework using a primal-dual algorithm for constrained diffusion, specifically designed for simulating point defects in materials.

Findings

Outperforms existing constrained diffusion methods in defect simulation.

Provides state-of-the-art, physically grounded defect structures for Bi2Te3.

Reduces computational costs of high-throughput defect simulations.

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 Bi2Te3, the proposed approach provides state-of-the-art performance generating physically grounded structures.