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

2026-02-22

AI Summary

High-throughput first-principles simulations of point defects are computationally expensive due to the need for large supercells and complex energy landscapes. To address this challenge, this work proposes a constraint-aware generative diffusion model integrated with a primal-dual optimization algorithm to efficiently generate physically plausible relaxed structures of inorganic solids containing point defects. The method achieves significant gains in generation efficiency while preserving atomic-level accuracy, outperforming existing constrained diffusion strategies. Experimental evaluation on six distinct point defect configurations in Bi₂Te₃ demonstrates that the generated structures exhibit both high quality and strong physical consistency, achieving state-of-the-art performance in the field.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Search and Optimization: Sampling/Simulation-based Search
• Constraint Satisfaction and Optimization: Other Foundations of Constraint Satisfaction

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

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.

Problem

• point defects
• first-principles simulations
• structure relaxation
• inorganic solids
• high-throughput

Innovation

• constrained diffusion
• point defects
• generative modeling
• primal-dual algorithm
• structure relaxation