Finetuning-Free Diffusion Model with Adaptive Constraint Guidance for Inorganic Crystal Structure Generation

2026-04-14

AI Summary

This work addresses the challenge of efficiently generating inorganic crystal structures that simultaneously satisfy physicochemical constraints, exhibit thermodynamic stability, and display structural diversity. The authors propose a fine-tuning-free, constraint-guided diffusion model that dynamically incorporates user-defined constraints during generation through an adaptive mechanism. By integrating graph neural networks with convex hull analysis, the method establishes a multi-stage validation pipeline to ensure both geometric plausibility and energetic stability. The approach innovatively realizes an interpretable and expert-intervenable paradigm for crystal generation, successfully designing novel structures in several canonical inorganic systems that are not only geometrically compliant but also thermodynamically stable, thereby demonstrating high accuracy, effectiveness, and strong generalization capability.

Technology Category

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

Application Category

• 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
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

The discovery of inorganic crystal structures with targeted properties is a significant challenge in materials science. Generative models, especially state-of-the-art diffusion models, offer the promise of modeling complex data distributions and proposing novel, realistic samples. However, current generative AI models still struggle to produce diverse, original, and reliable structures of experimentally achievable materials suitable for high-stakes applications. In this work, we propose a generative machine learning framework based on diffusion models with adaptive constraint guidance, which enables the incorporation of user-defined physical and chemical constraints during the generation process. This approach is designed to be practical and interpretable for human experts, allowing transparent decision-making and expert-driven exploration. To ensure the robustness and validity of the generated candidates, we introduce a multi-step validation pipeline that combines graph neural network estimators trained to achieve DFT-level accuracy and convex hull analysis for assessing thermodynamic stability. Our approach has been tested and validated on several classical examples of inorganic families of compounds, as case studies. As a consequence, these preliminary results demonstrate our framework's ability to generate thermodynamically plausible crystal structures that satisfy targeted geometric constraints across diverse inorganic chemical systems.

Problem

• inorganic crystal structure generation
• generative models
• thermodynamic stability
• physical and chemical constraints
• diffusion models

Innovation

• diffusion model
• adaptive constraint guidance
• inorganic crystal generation
• DFT-level accuracy
• thermodynamic stability