AI RESEARCH
ReciNet: Reciprocal Space-Aware Long-Range Modeling for Crystalline Property Prediction
arXiv CS.LG
•
ArXi:2502.02748v4 Announce Type: replace Predicting properties of crystals from their structures is a fundamental yet challenging task in materials science. Unlike molecules, crystal structures exhibit infinite periodic arrangements of atoms, requiring methods capable of capturing both local and global information effectively. However, current works fall short of capturing long-range interactions within periodic structures.