{
  "abstract": "Anomaly searches in large astronomical image datasets aim to identify rare objects for follow-up investigation. Yet the objects that are most statistically unusual are not necessarily those of greatest scientific relevance. We investigate whether pretrained vision-language models can directly assess scientific interest from natural-language instructions, enabling galaxy images to be ranked without labeled examples. We evaluate models on a 20,000-image Hubble Space Telescope sample that includes 167 reference anomalies previously identified through machine learning and expert inspection. By scoring images for scientific interest, Gemini 3.1 Flash-Lite places 98.2% of the reference anomalies within the highest-ranked ~2,000 images, at a present-day inference cost of approximately $5.05 per 10,000 images. We recover known gravitational lenses, jellyfish-galaxy candidates, and galaxies with visible jets, and release 102 high-scoring candidates for further investigation. These results show that an off-the-shelf vision-language model, without any training on the target data, offers a practical way to rank large image datasets by scientific relevance rather than rarity. The project code is available at https://github.com/TheCheng2005/Galaxy-Anomaly-Search/",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.37747",
  "author_total": 3,
  "authors": [
    {
      "name": "Yixuan Cheng"
    },
    {
      "name": "Nolan Koblischke"
    },
    {
      "name": "Jo Bovy"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/6d23449cxhhzh.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.37747",
  "fulltext_url": null,
  "id": "6d23449cxhhzh",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.37747",
  "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",
      "astro-ph.GA"
    ],
    [
      "arxiv",
      "astro-ph.IM"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2610.37747",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-27",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/6d23449cxhhzh.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:36:22Z",
      "native_id": "2610.37747",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.37747"
    }
  ],
  "subjects": [
    {
      "field": "astronomy",
      "origin": "arxiv:astro-ph.GA",
      "subfield": "galaxies"
    },
    {
      "field": "astronomy",
      "origin": "arxiv:astro-ph.IM",
      "subfield": "instrumentation-methods"
    }
  ],
  "title": "Identifying Scientifically Interesting Galaxies with Vision-Language Models",
  "title_text": "Identifying Scientifically Interesting Galaxies with Vision-Language Models",
  "type": "preprint",
  "updated_at": "2026-11-01T12:20:44Z",
  "url": "https://research.draconitic.com/paper/6d23449cxhhzh",
  "venue": "arXiv",
  "versions": []
}