Lang2Str: Two-Stage Crystal Structure Generation with LLMs and Continuous Flow Models

TL;DR

Lang2Str introduces a two-stage generative framework combining large language models and flow-based models to improve the diversity, validity, and control in crystal structure generation for material discovery.

Contribution

The paper presents a novel two-stage framework that leverages LLMs for high-level descriptions and flow models for precise structure decoding, enhancing flexibility and accuracy in material generation.

Findings

Achieves competitive performance in  initio material generation.

Generated structures closely match ground truth in geometry and energy.

Framework enables fine-grained control over material design.

Abstract

Generative models hold great promise for accelerating material discovery but are often limited by their inflexible single-stage generative process in designing valid and diverse materials. To address this, we propose a two-stage generative framework, Lang2Str, that combines the strengths of large language models (LLMs) and flow-based models for flexible and precise material generation. Our method frames the generative process as a conditional generative task, where an LLM provides high-level conditions by generating descriptions of material unit cells' geometric layouts and properties. These descriptions, informed by the LLM's extensive background knowledge, ensure reasonable structure designs. A conditioned flow model then decodes these textual conditions into precise continuous coordinates and unit cell parameters. This staged approach combines the structured reasoning of LLMs and the distribution modeling capabilities of flow models. Experimental results show that our method achieves competitive performance on \textit{ab initio} material generation and crystal structure prediction tasks, with generated structures exhibiting closer alignment to ground truth in both geometry and energy levels, surpassing state-of-the-art models. The flexibility and modularity of our framework further enable fine-grained control over the generation process, potentially leading to more efficient and customizable material design.