OxiGen: Oxidation-State-Aware Crystal Generation

2026-10-06

AI Summary

This study addresses the inability of existing crystal generation models to reproduce experimentally observed oxidation state distributions, which compromises the chemical plausibility of generated structures. To this end, we propose OxiGen, a diffusion model that incorporates oxidation-state awareness into the generative process for the first time. By explicitly representing oxidation states and enforcing global charge neutrality through finite-state automata for precise inference, OxiGen ensures rigorous charge balance. Experimental results demonstrate that OxiGen substantially improves oxidation state fidelity and achieves state-of-the-art performance in generating stable, unique, and novel crystals while maintaining high compositional validity. This work establishes an efficient new paradigm for the inverse design of inorganic materials.

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.

Problem

• crystal generation
• oxidation states
• generative models
• inorganic materials discovery

Innovation

• Crystal Generation
• Diffusion Model
• Oxidation State
• Finite-State Automaton
• Charge Neutrality