Metraipolis › archive › dc_c8c50ea5eaab
uFlowCSP: Crystal Structure Prediction using Mean flow generative models — arXiv:2609.09799
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.09799
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T07:26:26.627Z
- SHA-256 of the archived text
f3f56a71d8c74f6886f43f691ca693638a5a94407ef82a4752deb631a03dfb70- Stable URL of this page
https://metraipolis.com/documento/dc_c8c50ea5eaab
How to cite
uFlowCSP: Crystal Structure Prediction using Mean flow generative models — arXiv:2609.09799 — arXiv (en), https://arxiv.org/abs/2609.09799 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c8c50ea5eaab (Metraipolis archive dc_c8c50ea5eaab, sha256 f3f56a71d8c74f6886f43f691ca693638a5a94407ef82a4752deb631a03dfb70)
BibTeX
@misc{dcc8c50ea5eaab,
title = {uFlowCSP: Crystal Structure Prediction using Mean flow generative models — arXiv:2609.09799},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.09799},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c8c50ea5eaab; sha256 f3f56a71d8c74f6886f43f691ca693638a5a94407ef82a4752deb631a03dfb70},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09799. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Crystal structure prediction (CSP) is fundamental to computational materials discovery. Generative models including CDVAE, DiffCSP, FlowMM, and CrystalFlow learn stable-crystal distributions directly, but diffusion and flow-matching inference requires tens to thousands of sequential network evaluations per candidate. We introduce uFlowCSP, a MeanFlow-based CSP model that learns the average, rather than instantaneous, probability-flow velocity. It generates a complete structure in one to five evaluations, delivering 5x-58x faster inference with equal or better performance. A chemistry- and symmetry-aware Transformer uses canonical atom ordering, global composition, and per-token chemistry embeddings. A coarse crystal-system token is used only during training; it provides additive gains, particularly improving space-group agreement despite being absent at inference, which remains formula-only. On MP-20 with 20 candidates per target, one step matches CrystalFlow (78.38% vs. 78.34%) with 100x fewer evaluations and about 10x lower wall-clock time. Five steps reach 83.64%, exceeding CrystalFlow (78.34% at 2,000 evaluations) and DiffCSP (77.93% at about 20,000), while using 20x fewer evaluations. uFlowCSP generates 10,000 structures in 0.39-1.31 minutes, versus 6.5 for CrystalFlow and 76.1 for DiffCSP. Under CSPBench's energy-ranked top-five structure-and-space-group criterion, five-step uFlowCSP reaches 72%/72%/65% structure, space-group, and consensus match rates. CrystalFlow reaches 78%/73%/68% at 100 steps but falls to 49%/32%/31% at five. Thus, uFlowCSP improves accuracy per network evaluation, not merely peak accuracy. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.AI). Categorie arXiv: Materials Science (cond-mat.mtrl-sci) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.09799 — 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 2026-10-16T07:00:16.353Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).