{
  "abstract": "Foundation models are transforming artificial intelligence by enabling generalizable, data-efficient solutions across diverse domains and applications. However, the lack of large and diverse datasets remains a key barrier to their development in nanophotonics. This work presents MOCLIP (Metasurface Optics Contrastive Learning Pretrained), a nanophotonic foundation model that encodes metasurfaces’ structural and spectral information into a shared latent space via contrastive learning, using an experimentally acquired dataset with sample density approaching the scale of ImageNet-1K. The study demonstrates MOCLIP’s inverse design capabilities, including high-throughput zero-shot prediction at 2 ⋅ 105 samples per second, full-wafer design of an entire 4-inch substrate in minutes, and latent space optimization reaching 95% accuracy. This work further introduces an optical information storage concept that leverages MOCLIP to achieve a storage density of 0.1 Gbit/mm2 at the resolution limit, surpassing commercial optical media by a factor of six. Together, these results position MOCLIP as a scalable, versatile platform for next-generation photonic design and data-driven applications. The foundation model MOCLIP brings large-scale AI to nanophotonics. Trained on experimental wafer scale data, it designs metasurfaces at 200,000 samples per second with over 95% accuracy, enabling optical memory six times denser than commercial ones.",
  "abstract_shown": true,
  "affiliations": [
    "PRIMALIGHT, Faculty of Electrical Engineering; Applied Mathematics and Computational Science, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia",
    "PRIMALIGHT, Faculty of Electrical Engineering; Applied Mathematics and Computational Science, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia. andrea.fratalocchi@kaust.edu.sa"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Sergei Rodionov",
      "orcid": "0000-0002-8660-2162"
    },
    {
      "affs": [
        0
      ],
      "name": "Arturo Burguete Lopez",
      "orcid": "0000-0002-2318-1727"
    },
    {
      "affs": [
        0
      ],
      "name": "Maksim O. Makarenko",
      "orcid": "0000-0002-6761-8695"
    },
    {
      "affs": [
        0
      ],
      "name": "Qizhou Wang"
    },
    {
      "affs": [
        0
      ],
      "name": "Fedor Getman"
    },
    {
      "affs": [
        1
      ],
      "name": "Andrea Fratalocchi",
      "orcid": "0000-0001-6769-4439"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dbjs3vs9dsqm1.bib",
  "cited_by": 6,
  "doi": "10.1038/s41467-026-76714-x",
  "fulltext_url": null,
  "id": "dbjs3vs9dsqm1",
  "issns": [
    "2041-1723"
  ],
  "landing_url": "https://doi.org/10.1038/s41467-026-76714-x",
  "language": "en",
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2504|Metamaterials and Metasurfaces Applications"
    ]
  ],
  "openalex": "W7106667951",
  "pdf_url": "https://www.nature.com/articles/s41467-026-76714-x_reference.pdf",
  "pmcid": "PMC13582829",
  "pmid": "42749714",
  "published": "2026-08-19",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/dbjs3vs9dsqm1.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T13:21:07Z",
      "native_id": "W7106667951",
      "source": "openalex",
      "url": "https://doi.org/10.1038/s41467-026-76714-x"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2504|Metamaterials and Metasurfaces Applications",
      "subfield": "materials-polymers"
    }
  ],
  "title": "MOCLIP: a foundation model for large-scale nanophotonic inverse design",
  "title_text": "MOCLIP: a foundation model for large-scale nanophotonic inverse design",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T13:21:23Z",
  "url": "https://research.draconitic.com/paper/dbjs3vs9dsqm1",
  "venue": "Nature Communications",
  "versions": []
}