Arrow Research search
Back to AAAI

AAAI 2026

CrystalDiT: Simple Diffusion Transformers for Crystal Generation

Conference Paper AAAI Technical Track on Application Domains II Artificial Intelligence

Abstract

We present CrystalDiT, a diffusion transformer for crystal structure generation that achieves state-of-the-art performance by challenging the trend of architectural complexity. Instead of intricate, multi-stream designs, CrystalDiT employs a unified transformer that imposes a powerful inductive bias: treating lattice and atomic properties as a single, interdependent system. Combined with a periodic table-based atomic representation and a balanced training strategy, our approach achieves 8.78% SUN (Stable, Unique, Novel) rate on MP-20, substantially outperforming recent methods including FlowMM (4.21%) and MatterGen (3.66%). Notably, CrystalDiT generates 63.28% unique and novel structures while maintaining comparable stability rates, demonstrating that architectural simplicity can be more effective than complexity for materials discovery. Our results suggest that in data-limited scientific domains, carefully designed simple architectures outperform sophisticated alternatives that are prone to overfitting.

Authors

Keywords

No keywords are indexed for this paper.

Context

Venue
AAAI Conference on Artificial Intelligence
Archive span
1980-2026
Indexed papers
28718
Paper id
391079885541451182
v2026.09.13