{
  "abstract": "Machine learning surrogates for density functional theory (DFT) have been increasingly used to reduce the cost of first-principles calculations. In this arena, predicting real-space electron densities offers a scalable and transferable initialization for self-consistent field (SCF) procedures. However, current methods face a clear dilemma. That is, grid-based architectures incur a high computational cost, while basis-set methods fail to capture the structural correlations inherent in the coefficient space. Here, we develop OrbFlow, an $\\mathrm{SE}(3)$-equivariant generative model that predicts Gaussian-type orbital (GTO) coefficients via flow matching. OrbFlow retains the efficiency of a compact atom-centered basis while replacing pointwise regression with a learned probability path over the full coefficient space. It is trained through a two-phase trajectory curriculum that mitigates discretization drift during numerical integration. OrbFlow achieves state-of-the-art accuracy on QM9, reducing density error by 13.6% relative to the previous best model, and reduces error by 51% to 63% on every molecule of the MD benchmark relative to the strongest prior method sharing its basis. The predicted density also cuts SCF iterations by up to 68% with zero-shot transfer to unseen exchange-correlation functionals and recovers dipole and quadrupole moments to within a few percent of DFT references without any SCF calculation.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.02651",
  "author_total": 5,
  "authors": [
    {
      "name": "Chenxing Liang"
    },
    {
      "name": "Chengdong Wang"
    },
    {
      "name": "Yuchao Lin"
    },
    {
      "name": "Xiaofeng Qian"
    },
    {
      "name": "Shuiwang Ji"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/fqhw2jg14e8qz.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.02651",
  "fulltext_url": null,
  "id": "fqhw2jg14e8qz",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.02651",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "physics.chem-ph"
    ],
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7220390198",
  "pdf_url": "https://arxiv.org/pdf/2610.02651",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-02",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/fqhw2jg14e8qz.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:26:45Z",
      "native_id": "2610.02651",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.02651"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "arxiv:physics.chem-ph",
      "subfield": "physical"
    }
  ],
  "title": "Equivariant Flow Matching for Electron Density Prediction",
  "title_text": "Equivariant Flow Matching for Electron Density Prediction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:26:45Z",
  "url": "https://research.draconitic.com/paper/fqhw2jg14e8qz",
  "venue": "arXiv",
  "versions": []
}