{
  "abstract": "Conventional diffractive deep neural networks (D2NNs) treat polarization as independent channels and rely on scalar or semi-vectorial propagation models, which neglect cross polarization coupling and vector diffraction. Here we propose a vector D2NN (V-D2NN) that embeds the full vector angular spectrum method into the end-to-end training pipeline. This physically rigorous framework describes vectorial light-matter interactions across cascaded diffractive layers, enabling direct optimization of polarization conversion, spin-orbit coupling, and vectorial interference without external polarization optics. We demonstrate the V-D2NN on polarization-multiplexed tasks--ector beam generation, polarization dependent imaging and classification, and multiple channel optical encryption--where it consistently outperforms scalar and semi-vectorial counterparts. In longitudinal-field engineering, the V-D2NN actively shapes a prescribed longitudinal field with a normalized correlation of 0.839, a capability inaccessible to scalar-propagation models. An open-source training framework is also provided to support further development of vectorial diffractive optics for computing, sensing, and communications.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.11274",
  "author_total": 5,
  "authors": [
    {
      "name": "Shengmei Zhao"
    },
    {
      "name": "Gongyuan Wang"
    },
    {
      "name": "Zhiwan Wang"
    },
    {
      "name": "Jianan Shao"
    },
    {
      "name": "Haolin Liu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8z844py0vqxtd.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.11274",
  "fulltext_url": null,
  "id": "8z844py0vqxtd",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.11274",
  "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",
      "physics.optics"
    ],
    [
      "openalex",
      "1702|Neural Networks and Reservoir Computing"
    ]
  ],
  "openalex": "W7221143640",
  "pdf_url": "https://arxiv.org/pdf/2610.11274",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-08",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/8z844py0vqxtd.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:54Z",
      "native_id": "2610.11274",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.11274"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.optics",
      "subfield": "optics-photonics"
    }
  ],
  "title": "Full-Vector Diffractive Deep Neural Networks",
  "title_text": "Full-Vector Diffractive Deep Neural Networks",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:54Z",
  "url": "https://research.draconitic.com/paper/8z844py0vqxtd",
  "venue": "arXiv",
  "versions": []
}