← Back to all news
arXiv Machine Learning By Anmar Karmush, Cedric Mathieu Brandenburg, Soheil Ershadrad, Johanna Rosen, Michael Felsberg, Filip Ekstr\"om Kelvinius

SymADiT: Symmetry-Aware Crystal Generation with Latent Flow Matching

Read the original on arXiv Machine Learning →

SymADiT is a symmetry‑aware variant of the All‑atom Diffusion Transformer (ADiT) designed for crystal generation. It uses Wyckoff‑based crystal representations and enforces symmetry constraints from the crystal’s space group and atom positions during latent‑space generative modeling. The approach yields stable, symmetric, and physically plausible crystals while maintaining competitive performance against both symmetry‑aware and symmetry‑agnostic models.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Oct 22

Orbitol: Crystal Generation on Wyckoff Orbits

Orbitol is a crystal generation model that uses Wyckoff-orbit tokens instead of atom tokens, enabling direct control over the space group of generated structures. It produces structures two to three orders of magnitude faster than symmetry‑aware baselines and achieves higher success rates in generating stable, novel structures that retain the requested symmetry. The authors also introduce SPARC, a score combining space‑group retention with distribution agreement, and demonstrate Orbitol’s effectiveness in generating high‑quality piezoelectric candidates with superior figures of merit.

By Ivan \v{Z}ugec, Joshua Rosenthal, Ivor Lon\v{c}ari\'c, Jan-Willem van de Meent, Tin Had\v{z}i Veljkovi\'c
llmsdiffusion
More like this →