{
  "abstract": "Artificial intelligence is increasingly applied to inverse materials design, including crystals and molecules. For molecular systems, multimodal models that integrate chemical structures with natural language have enabled flexible, instruction-driven reasoning. However, approaches for crystalline materials remain limited by the scarcity and imbalanced bias of available crystal datasets and the weak semantic supervision provided by peer-reviewed literature. We introduce a contrastive language-crystals model (CLaC), a multimodal contrastive learning framework that aligns crystal structures with natural language, pre-trained on property-conditioned synthetic narratives of crystal structure-text pairs generated by language models. Here we show that, compared with models trained on literature-derived text, this property-grounded synthetic supervision enables semantic alignment unachievable with existing academic corpora. Embedding-space analyses reveal structured associations between language and crystal structures. These results establish a foundation for zero-shot, instruction-driven reasoning in crystalline materials. CLaC is a contrastive language-crystals model that aligns crystal structures with natural language using property-conditioned synthetic narratives, enabling zero-shot, instruction driven reasoning unachievable with literature-derived text alone.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA",
    "Department of Materials Science and Engineering, Ulsan National Institute of Science and Technology, Ulju-gun, Ulsan, Republic of Korea",
    "Department of Nuclear Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA",
    "Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Urbana, IL, USA",
    "Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA. elsao@mit.edu",
    "MIT-IBM Watson AI Lab, Massachusetts Institute of Technology, Cambridge, MA, USA. elsao@mit.edu",
    "Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA. liju@mit.edu",
    "Department of Nuclear Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA. liju@mit.edu",
    "MIT-IBM Watson AI Lab, Massachusetts Institute of Technology, Cambridge, MA, USA. liju@mit.edu"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0,
        1,
        2
      ],
      "name": "Yang Jeong Park",
      "orcid": "0000-0002-3773-7407"
    },
    {
      "affs": [
        3
      ],
      "name": "Mayank Kumaran"
    },
    {
      "affs": [
        0
      ],
      "name": "Chia-Wei Hsu"
    },
    {
      "affs": [
        4,
        5
      ],
      "name": "Elsa Olivetti",
      "orcid": "0000-0002-8043-2385"
    },
    {
      "affs": [
        6,
        7,
        8
      ],
      "name": "Ju Li",
      "orcid": "0000-0002-7841-8058"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/1swd6wjm2c0eg.bib",
  "cited_by": 7,
  "doi": "10.1038/s41467-026-76378-7",
  "fulltext_url": null,
  "id": "1swd6wjm2c0eg",
  "issns": [
    "2041-1723"
  ],
  "landing_url": "https://doi.org/10.1038/s41467-026-76378-7",
  "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",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7204272178",
  "pdf_url": "https://www.nature.com/articles/s41467-026-76378-7_reference.pdf",
  "pmcid": "PMC13616920",
  "pmid": "42802153",
  "published": "2026-08-26",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/1swd6wjm2c0eg.ris",
  "sources": [
    {
      "first_seen": "2026-11-05T13:21:14Z",
      "native_id": "W7204272178",
      "source": "openalex",
      "url": "https://doi.org/10.1038/s41467-026-76378-7"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "Scaling multimodal materials representation learning with synthetic narratives",
  "title_text": "Scaling multimodal materials representation learning with synthetic narratives",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T13:21:23Z",
  "url": "https://research.draconitic.com/paper/1swd6wjm2c0eg",
  "venue": "Nature Communications",
  "versions": []
}