{
 "id": "jrzhang/TextVQA_GT_bbox",
 "owner": "jrzhang",
 "name": "TextVQA_GT_bbox",
 "downloads": 245,
 "likes": 4,
 "last_modified": "2025-04-10T19:29:32.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "question-answering",
  "text-generation",
  "image-to-text"
 ],
 "citation": "@article{zhang2025mllms,\n  title={MLLMs know where to look: Training-free perception of small visual details with multimodal LLMs},\n  author={Zhang, Jiarui and Khayatkhoei, Mahyar and Chhikara, Prateek and Ilievski, Filip},\n  journal={arXiv preprint arXiv:2502.17422},\n  year={2025}\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "4a0fae0da919af44db46d93ab1a1e128daad2de6",
 "stated_evidence": "https://huggingface.co/datasets/jrzhang/TextVQA_GT_bbox/blob/4a0fae0da919af44db46d93ab1a1e128daad2de6/README.md",
 "file_evidence": "https://huggingface.co/datasets/jrzhang/TextVQA_GT_bbox/tree/4a0fae0da919af44db46d93ab1a1e128daad2de6",
 "card_nc": false
}