2601.08151v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:15.101000Z",
      "hash": "534467476c965ba3992dcd5533fef18e4f8e9712c380d7010d61a7b67251b19f",
      "id": "796d3361-33f0-467d-9009-30a10c5ecd47",
      "source": {
        "execution_id": "d448cd20-8eb8-47a5-9986-a4f647df0f6c",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "534467476c965ba3992dcd5533fef18e4f8e9712c380d7010d61a7b67251b19f",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.08151v1.pdf",
      "size": 1460864
    },
    "source": {
      "execution_id": "4292254a-8223-43fa-86ac-e12b3c4b6bbf",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 11,
      "producer": "pikepdf 8.15.1",
      "title": "Where Does Vision Meet Language? Understanding and Refining Visual Fusion in MLLMs via Contrastive Attention",
      "version": "1.7"
    },
    "source": {
      "execution_id": "5a458038-79a2-4ca8-88f9-d02044a777c0",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}