Search papers, labs, and topics across Lattice.
OxiGen, an oxidation-state-aware crystal diffusion model, explicitly incorporates oxidation states during generation to improve the fidelity of generated inorganic crystals. By enforcing global charge neutrality via a structured output layer with exact inference over a finite-state automaton, OxiGen overcomes the limitations of prior models that poorly reproduced observed oxidation-state distributions. Empirically, OxiGen achieves superior oxidation-state fidelity, generates more stable, unique, and novel crystals, and maintains high compositional validity.
Generative models can now produce inorganic crystals with oxidation-state distributions mirroring real-world synthesis, significantly boosting discovery potential.
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.
