发表机构
NVIDIA; Massachusetts Institute of Technology; Harvard University; The MITRE Corporation; University of California, Berkeley; Robert Bosch Research and Technology Center（英伟达; 麻省理工学院; 哈佛大学; MITRE公司; 加州大学伯克利分校; 罗伯特·博世研究技术中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
DynaCrys是一种新型晶体生成模型，通过耦合符号扩散过程实现空间群与Wyckoff占据数、元素的共同演化，在稳定新型晶体发现中表现一流，且采样快速、结构位移低。
AI 中文摘要
新型晶体材料的搜索涵盖了极其庞大的成分与结构空间，在该空间中生成候选材料需要联合建模离散的晶体学对称性、元素组成以及连续几何结构。我们提出DynaCrys，这是一种用于晶体的生成模型，其中空间群通过耦合的符号扩散过程与Wyckoff占据数和元素共同演化。结构化的空间群转换遵循晶体学的子群-母群关系。当空间群发生变化时，一个共享的预训练对称码本为受合法性约束的随机解码器和受对称性约束的晶体几何模型提供相应Wyckoff词汇的共同表示。通过使用两个独立的弛豫与评估引擎进行大规模评估，DynaCrys在对称性感知的稳定、独特且新型晶体的发现中实现了一流的性能，无论是总体而言还是在非平凡弛豫后对称性的额外要求下均是如此。它还支持快速采样，同时生成的结构具有始终较低的弛豫诱导结构位移。
英文摘要
The search for new crystalline materials spans an enormous compositional and structural space. Generating candidates in this space requires jointly modeling discrete crystallographic symmetry, elemental composition, and continuous geometry. We introduce DynaCrys, a generative model for crystals in which the space group co-evolves with Wyckoff occupations and elements through a coupled symbolic diffusion process. The structured space-group transitions follow crystallographic group-subgroup relations. As the space group changes, a shared, pretrained symmetry codebook provides both the legality-constrained stochastic decoder and the symmetry-constrained crystal-geometry model with a common representation of the corresponding Wyckoff vocabulary. Across large-scale evaluations using two independent relaxation-and-evaluation engines, DynaCrys achieves best-in-class performance in symmetry-aware discovery of stable, unique, and novel crystals, both overall and under the additional requirement of nontrivial post-relaxation symmetry. It also enables fast sampling while generating structures with consistently low relaxation-induced structural displacements.
