Metraipolis › archive › dc_44b31ce9975d

Transformer-inspired architectures make machine-learned electron densities accurate and transferable enough to bypass self-consistency — arXiv:2610.39687

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.39687
License (as archived): CC0-1.0
Archived: 2026-11-01T02:27:15.916Z
SHA-256 of the archived text: 8d8895ee9f53135f4442ef8c06ddbb0260bd9ffda3840410190157bdfb162a27
Stable URL of this page: https://metraipolis.com/documento/dc_44b31ce9975d

How to cite

Transformer-inspired architectures make machine-learned electron densities accurate and transferable enough to bypass self-consistency — arXiv:2610.39687 — arXiv (en), https://arxiv.org/abs/2610.39687 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_44b31ce9975d (Metraipolis archive dc_44b31ce9975d, sha256 8d8895ee9f53135f4442ef8c06ddbb0260bd9ffda3840410190157bdfb162a27)

BibTeX

@misc{dc44b31ce9975d,
  title = {Transformer-inspired architectures make machine-learned electron densities accurate and transferable enough to bypass self-consistency — arXiv:2610.39687},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39687},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_44b31ce9975d; sha256 8d8895ee9f53135f4442ef8c06ddbb0260bd9ffda3840410190157bdfb162a27},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39687. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce machine learning models that accurately predict the electron density, the central variable of density functional theory. They are built on Transformer-inspired architectures, which require little computation per parameter and can therefore be enlarged at low cost. The proposed models, SwinUNETR-V2 and its attention-free counterpart NeXtUNETR, achieve state-of-the-art accuracy on QM9, with normalized mean absolute errors in the density averaging 0.075% and 0.046%, respectively. The predicted densities are accurate enough to bypass the self-consistent iteration: a single Kohn-Sham step reproduces the self-consistent electronic structure. For NeXtUNETR, the median errors are 0.036 meV in the total energy, 0.65 meV/angstrom in the forces and 1.8 meV in the HOMO-LUMO gap. The forces not only recover the self-consistent minima in geometry optimization but also successfully drive ab initio molecular dynamics. Fine-tuned on small datasets, both networks also transfer accurately to systems containing elements absent from QM9 or larger than its molecules.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Chemical Physics (physics.chem-ph) ; Machine Learning (cs.LG); Computational Physics (physics.comp-ph).
Pagina del lavoro: https://arxiv.org/abs/2610.39687 — 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 2026-11-01T02:12:44.310Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).