OxiGen: Oxidation-State-Aware Crystal Generation
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.
Related
- Automated mode-aware design of nonlinear photonic crystal cavities for intrinsic second harmonic generation
- SymADiT: Symmetry-Aware Crystal Generation with Latent Flow Matching
- Symmetry- and Property-Aware Crystal Generation with Reinforcement Learning for Inverse Materials Design
- 266 nm generation performance of NSBBF crystal improved by elevating the operating temperature
- Text-guided flow matching enables sample-efficient crystal structure generation
BibTeX
@misc{john2026oxigen,
title = {{OxiGen: Oxidation-State-Aware Crystal Generation}},
author = {Dylan John and Kim E. Jelfs and Alex M. Ganose and Eleonora Giunchiglia},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.08296},
eprint = {2610.08296},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.08296},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - OxiGen: Oxidation-State-Aware Crystal Generation
AU - Dylan John
AU - Kim E. Jelfs
AU - Alex M. Ganose
AU - Eleonora Giunchiglia
PY - 2026
DA - 2026/10/06
PB - arXiv
DO - 10.48550/arxiv.2610.08296
UR - https://arxiv.org/abs/2610.08296
AB - 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.
ER -