{
  "abstract": "Density functional theory (DFT) gives the electronic structure of materials, but its cost limits large-supercell calculations and materials screening. Machine-learned Hamiltonians bypass the self-consistent cycle but are usually system-specific; universal ones could cover new compositions and disordered solids. Such models must generalize across chemistry and keep downstream properties physical, while staying inexpensive for large cells. Here we introduce UniTB, a universal E(3) equivariant Hamiltonian representation framework that integrates physical priors rooted in density-functional tight-binding theory with deep learning. UniTB's network, which corrects a prior Hamiltonian, generalizes across chemistry through a mixture of experts routed by that prior and a charge-equilibration head as in self-consistent-charge tight binding. A projection bounds band shifts from the prior, suppressing spurious states and keeping downstream properties physical. We provide the fastest SO(2) tensor-product GPU kernels for the network. The variant UniTB-Flash assembles its prior from two-center tables at $O(N)$ cost for $N$ atoms, against $O(N\\log N)$ on a grid. Trained on 29,242 crystals, UniTB reaches a 0.48 meV matrix-element error on nonmagnetic test crystals spanning 68 elements. Without amorphous training data, both models agree with DFT optics and conductivity of amorphous Ge-Sb-Te. UniTB-Flash ranks candidates with no significant difference from UniTB, whose property values are more accurate; together they screen 16,195 crystals for five application domains of industrial relevance.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.36135",
  "author_total": 6,
  "authors": [
    {
      "name": "Mingkang Liu"
    },
    {
      "name": "Zhanghao Zhouyin"
    },
    {
      "name": "Guanghui Wang"
    },
    {
      "name": "Daye Zheng"
    },
    {
      "name": "Lei Shen"
    },
    {
      "name": "Qiangqiang Gu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dxdqj8xm7vzs8.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.36135",
  "fulltext_url": null,
  "id": "dxdqj8xm7vzs8",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.36135",
  "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.mtrl-sci"
    ],
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7224124227",
  "pdf_url": "https://arxiv.org/pdf/2610.36135",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-26",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/dxdqj8xm7vzs8.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:35:50Z",
      "native_id": "2610.36135",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.36135"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:cond-mat.mtrl-sci",
      "subfield": "condensed-matter"
    }
  ],
  "title": "Physical structure as an organizing principle for universal Hamiltonian learning",
  "title_text": "Physical structure as an organizing principle for universal Hamiltonian learning",
  "type": "preprint",
  "updated_at": "2026-10-30T12:35:50Z",
  "url": "https://research.draconitic.com/paper/dxdqj8xm7vzs8",
  "venue": "arXiv",
  "versions": []
}