Metraipolis › archive › dc_a181ddf42b00
GLASS: Global Latent Aggregation with Slot-based Set Decoding for Scalable All-Atom Crystal Generation — arXiv:2609.37158
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37158
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T17:30:36.345Z
- SHA-256 of the archived text
b710c74adb78a9da57849a537896a801b3540697d3844604fec0b896555e9c8e- Stable URL of this page
https://metraipolis.com/documento/dc_a181ddf42b00
How to cite
GLASS: Global Latent Aggregation with Slot-based Set Decoding for Scalable All-Atom Crystal Generation — arXiv:2609.37158 — arXiv (en), https://arxiv.org/abs/2609.37158 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a181ddf42b00 (Metraipolis archive dc_a181ddf42b00, sha256 b710c74adb78a9da57849a537896a801b3540697d3844604fec0b896555e9c8e)
BibTeX
@misc{dca181ddf42b00,
title = {GLASS: Global Latent Aggregation with Slot-based Set Decoding for Scalable All-Atom Crystal Generation — arXiv:2609.37158},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37158},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a181ddf42b00; sha256 b710c74adb78a9da57849a537896a801b3540697d3844604fec0b896555e9c8e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37158. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generative models for crystals enable the discovery of novel structures, but scaling all-atom generation to larger systems such as metal--organic frameworks remains challenging. We connect this difficulty to the correspondence problem of particle-space generation. Even on a single fixed target set, index-free permutation-equivariant particle flows require substantially more training for reliable generation as set size and density increase, under both independent and optimal-transport couplings. To resolve this challenge, we introduce GLASS---Global Latent Aggregation with Slot-based Set Decoding, which encodes structures in a permutation-invariant global latent space and learns their distribution via flow matching. A learned-slot decoder constructs all atoms in parallel, removing atom-wise correspondence from generative transport. On MP20, GLASS is competitive with particle-space models, and flow training can reach the validity of the training data at every structure size. On a QMOF subset, GLASS generates MOFs with up to 150 atoms per unit cell without conditioning on building blocks, topology, or composition, and approaches the structural validity of the training data. On both datasets, flow training exposes a validity--novelty tradeoff, and MOF novelty remains limited by autoencoder generalization on the available data. These results show that separating correspondence assignment from generative transport provides a simple route toward high-validity generation of larger atomistic systems. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Materials Science (cond-mat.mtrl-sci). Pagina del lavoro: https://arxiv.org/abs/2609.37158 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T16:59:48.295Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).