arXiv：cs.LG· Dylan John, Kim E. Jelfs, Alex M. Ganose, Eleonora Giunchiglia·· 4 小时前AI 评分30
OxiGen：氧化态感知的晶体生成模型
OxiGen: Oxidation-State-Aware Crystal Generation
AI 导读
OxiGen 是一个在生成过程中显式表示氧化态的晶体扩散模型，通过有限状态自动机上的结构化输出层实现精确推理，从构造上强制全局电荷中性。实验显示其显著提升氧化态保真度，在评估方法中生成稳定、唯一且新颖晶体的比例最高，且在性质条件约束下仍保持高成分有效性。
正文
Abstract:Generative models have the potential to accelerate inorganic materials discovery by enabling inverse design, but generating experimentally realisable crystals remains challenging. Oxidation states are widely used to assess the compositional validity of crystals and guide inorganic materials discovery. While existing generative models for crystals can generate materials with charge-neutral oxidation-state assignments, they poorly reproduce the distributions of oxidation states observed in synthesised materials. To address this limitation, we propose OxiGen, an oxidation-state-aware crystal diffusion model that explicitly represents oxidation states during generation. OxiGen enforces global charge neutrality by construction using a structured output layer with exact inference over a finite-state automaton. Empirically, OxiGen substantially improves oxidation-state fidelity, generates the highest rate of stable, unique, and novel crystals among evaluated methods, and maintains high compositional validity even under property conditioning.
| Comments: | 27 pages, 4 figures |
| Subjects: | Machine Learning (cs.LG); Materials Science (cond-mat.mtrl-sci) |
| Cite as: | arXiv:2610.08296 [cs.LG] |
| (or arXiv:2610.08296v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.08296 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Dylan John [view email]
[v1]
Tue, 6 Oct 2026 13:01:35 UTC (1,028 KB)
来源：arXiv：cs.LG · arxiv.org