{
  "abstract": "All-optical diffractive neural networks (DNNs) offer low latency, low energy consumption, and massive parallelism. However, their scalability in terms of network scale and multi-task processing remains limited. Here, we experimentally demonstrate a large-scale metasurface-based diffractive learning machine for angle-multiplexed multi-task processing. Our system employs a metasurface-based reflection cavity to realize a five-layer DNN comprising 115 million fixed, untrained diffractive nodes within a compact volume of 216 mm^3. By integrating this large-scale, untrained DNN with a lightweight, trainable digital backend containing only 7,680 parameters, our system experimentally achieves an accuracy of 95.3% on the standard full-scale CIFAR-10 dataset, significantly outperforming previous optical neural networks and rivaling large-scale digital models. Using a novel incident-angle-multiplexing scheme, our system experimentally achieves parallel processing of 11 tasks with negligible performance degradation, representing the largest multi-task processing capacity reported to date. Our work provides a scalable and energy-efficient solution for high-performance edge computing.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.25792",
  "author_total": 7,
  "authors": [
    {
      "name": "Mingcheng Luo"
    },
    {
      "name": "Jianmin Xiong"
    },
    {
      "name": "Jiayong Peng"
    },
    {
      "name": "Jingtian Hu"
    },
    {
      "name": "Hongwei Chen"
    },
    {
      "name": "Chester Shu"
    },
    {
      "name": "Chaoran Huang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/djs0s3c6f4fbx.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.25792",
  "fulltext_url": null,
  "id": "djs0s3c6f4fbx",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.25792",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "physics.optics"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2609.25792",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-22",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/djs0s3c6f4fbx.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:23:39Z",
      "native_id": "2609.25792",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.25792"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.optics",
      "subfield": "optics-photonics"
    }
  ],
  "title": "Meta-Optics-Based Diffractive Learning Machine for Angle-Multiplexed Multi-Task Processing",
  "title_text": "Meta-Optics-Based Diffractive Learning Machine for Angle-Multiplexed Multi-Task Processing",
  "type": "preprint",
  "updated_at": "2026-10-30T12:23:39Z",
  "url": "https://research.draconitic.com/paper/djs0s3c6f4fbx",
  "venue": "arXiv",
  "versions": []
}