Where Should Physics Enter a Molecular Crystal Generator?
Quick summary
arXiv:2609.36398v1 Announce Type: cross Abstract: Generative models make molecular crystal structure prediction fast, but their samples still exhibit geometric and packing violations. Physics can be introduced during training, post-training, or inference, yet these choices are rarely compared with the generator and physical signal held fixed. We introduce CrystAF, an all-atom crystal flow-map generation model, and use it with the UMA interatomic potential to systematically study where physics should enter. Post-training learns physical preferences directly into CrystAF, improving molecular val
Key takeaways
- arXiv:2609.36398v1 Announce Type: cross Abstract: Generative models make molecular crystal structure prediction fast, but their samples still exhibit geometric and packing violations.
- Physics can be introduced during training, post-training, or inference, yet these choices are rarely compared with the generator and physical signal held fixed.
- We introduce CrystAF, an all-atom crystal flow-map generation model, and use it with the UMA interatomic potential to systematically study where physics should enter.
Why it matters
“Where Should Physics Enter a Molecular Crystal Generator?” highlights the need for repeatable measurement rather than a single impressive demonstration. Independent validation across datasets and clearly stated limitations determine whether a result can guide product decisions.
Member comments