Can a lightweight Transformer compete in crystal generation without equivariance?

We show that it can.

Crystalite combines chemistry-aware priors with geometric attention biases for:

– SOTA CSP
– best S.U.N. among all baselines
– much faster sampling

More info below! 👇 pic.twitter.com/IkyAOruOu9

— Tin Hadzi Veljkovic (@HvTin) 3 avril 2026

Can a lightweight Transformer compete in crystal generation without equivariance? We show that it can. Crystalite combines chemistry-aware priors with geometric attention biases for: – SOTA CSP – best S.U.N. among all baselines – much faster sampling More info below! 👇

→ View original post on X — @nandodf, 2026-04-03 10:33 UTC