Multimodal Crystal Flow: Any-to-Any Modality Generation for Unified Crystal Modeling
This work addresses the problem of fragmented modeling in crystal generation for materials science, though it is incremental as it builds on existing flow models.
The paper tackles the lack of a unified framework for crystal generation tasks by proposing Multimodal Crystal Flow (MCFlow), which achieves competitive performance on MP-20 and MPTS-52 benchmarks against task-specific baselines.
Crystal modeling spans a family of conditional and unconditional generation tasks across different modalities, including crystal structure prediction (CSP) and \emph{de novo} generation (DNG). While recent deep generative models have shown promising performance, they remain largely task-specific, lacking a unified framework that shares crystal representations across different generation tasks. To address this limitation, we propose \emph{Multimodal Crystal Flow (MCFlow)}, a unified multimodal flow model that realizes multiple crystal generation tasks as distinct inference trajectories via independent time variables for atom types and crystal structures. To enable multimodal flow in a standard transformer model, we introduce a composition- and symmetry-aware atom ordering with hierarchical permutation augmentation, injecting strong compositional and crystallographic priors without explicit structural templates. Experiments on the MP-20 and MPTS-52 benchmarks show that MCFlow achieves competitive performance against task-specific baselines across multiple crystal generation tasks.