2025/06/27 by Jithendaraa Subramanian, Subramanian, Jithendaraa, Linda Hung +7
Biochemistry, Genetics and Molecular Biology · Materials Science · #Advanced Electron Microscopy Techniques and Applications #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Machine Learning in Materials Science #Materials Science (cond-mat.mtrl-sci) #X-ray Diffraction in Crystallography
paper · pdf · doi:10.48550/arxiv.2507.01054
openalex publication_date 2025/06/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Recent advances in materials discovery have been driven by structure-based models, particularly those using crystal graphs. While effective for computational datasets, these models are impractical for real-world applications where atomic structures are often unknown or difficult to obtain. We propose a scalable multimodal framework that learns directly from elemental composition and X-ray diffraction (XRD) -- two of the more available modalities in experimental workflows without requiring crystal structure input. Our architecture integrates modality-specific encoders with a cross-attention fusion module and is trained on the 5-million-sample Alexandria dataset. We present masked XRD modeling (MXM), and apply MXM and contrastive alignment as self-supervised pretraining strategies. Pretraining yields faster convergence (up to 4.2x speedup) and improves both accuracy and representation quality. We further demonstrate that multimodal performance scales more favorably with dataset size than unimodal baselines, with gains compounding at larger data regimes. Our results establish a path toward structure-free, experimentally grounded foundation models for materials science.