AI RESEARCH
CrystalREPA: Transferring Physical Priors from Universal MLIPs to Crystal Generative Models
arXiv CS.LG
•
ArXi:2605.08960v1 Announce Type: cross Crystal generative models mainly learn what stable crystals look like, with little explicit supervision for what makes them stable. We reveal a substantial representation gap between state-of-the-art crystal generative models and pretrained universal machine learning interatomic potentials (MLIPs) via energy probing, and show this gap can be closed by a simple