The discovery of new materials is very important to the field of materials science. When researchers explore new materials, they often have expected performance requirements for their crystal structure. In recent years, data-driven methods have made great progress in the direction plane of crystal structure generation, but there is still a lack of methods that can effectively map material properties to crystal structure. In this paper, we propose a Crystal DiT model to generate the crystal structure from the expected material properties by embedding the material properties and combining the symmetry information predicted by the large language model. Experimental verification shows that our proposed method has good performance.

翻译：新材料的发现对材料科学领域至关重要。当研究人员探索新材料时，通常对其晶体结构具有预期的性能要求。近年来，数据驱动方法在晶体结构生成方向取得了巨大进展，但仍缺乏能够有效将材料性能映射至晶体结构的方法。本文提出了一种Crystal DiT模型，通过嵌入材料性能并结合大语言模型预测的对称性信息，从预期材料性能生成晶体结构。实验验证表明，我们提出的方法具有良好的性能。