{
  "abstract": "Simulating strongly correlated fermions remains a long-standing challenge due to the exponential complexity of the Hilbert space and the intricate sign structure of many-body wavefunctions. We introduce a variational framework centered on a neural network backflow transformation that combines deep learning with variational Monte Carlo. The proposed ansatz employs a multi-determinant expansion with low-rank shifts to capture non-local correlations and complex sign structures. Applied to the two-dimensional Hubbard model at both half-filling and $1/8$ doping, the method achieves energies within $0.45\\%$ of auxiliary-field quantum Monte Carlo at half-filling and captures intertwined charge- and spin-density stripe patterns at $1/8$ doping. These results demonstrate the potential of this framework as a scalable and interpretable approach to variational simulations of strongly correlated fermionic systems.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.26544",
  "author_total": 3,
  "authors": [
    {
      "name": "Tianshu Huang"
    },
    {
      "name": "Xiaowei Ou"
    },
    {
      "name": "Vidvuds Ozolins"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8ca7fezftnnrc.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.26544",
  "fulltext_url": null,
  "id": "8ca7fezftnnrc",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.26544",
  "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",
      "cond-mat.str-el"
    ],
    [
      "arxiv",
      "cond-mat.supr-con"
    ],
    [
      "arxiv",
      "quant-ph"
    ],
    [
      "openalex",
      "3107|Quantum many-body systems"
    ]
  ],
  "openalex": "W7214086220",
  "pdf_url": "https://arxiv.org/pdf/2609.26544",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-22",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/8ca7fezftnnrc.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:23:39Z",
      "native_id": "2609.26544",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.26544"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:cond-mat.str-el",
      "subfield": "condensed-matter"
    },
    {
      "field": "physics",
      "origin": "arxiv:quant-ph",
      "subfield": "quantum"
    }
  ],
  "title": "Neural Network Backflow with Low-Rank Multi-Determinant Updates",
  "title_text": "Neural Network Backflow with Low-Rank Multi-Determinant Updates",
  "type": "preprint",
  "updated_at": "2026-10-30T12:23:39Z",
  "url": "https://research.draconitic.com/paper/8ca7fezftnnrc",
  "venue": "arXiv",
  "versions": []
}