2601.11632v1.pdf

{
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "af188217529fde189ce2650a692e4a33db925f16f3cde4778bf6d1ebe99dbe4a",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.11632v1.pdf",
      "size": 1853888
    },
    "source": {
      "execution_id": "fbdfa233-c1eb-400f-ad8b-2dfc236c9f68",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 14,
      "producer": "pikepdf 8.15.1",
      "title": "KG-ViP: Bridging Knowledge Grounding and Visual Perception in Multi-modal LLMs for Visual Question Answering",
      "version": "1.7"
    },
    "source": {
      "execution_id": "1ae18011-7ee7-44b7-a97e-add11b7486cc",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}