{
 "id": "336labs/VisionEncoder-Eval-ReproData",
 "owner": "336labs",
 "name": "VisionEncoder-Eval-ReproData",
 "downloads": 1237,
 "likes": 0,
 "last_modified": "2026-10-07T05:46:32.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "upstream-data-and-model-terms",
 "licence_link": "https://huggingface.co/datasets/336labs/VisionEncoder-Eval-ReproData/blob/main/LICENSES.md",
 "file_licence": null,
 "licence_files": [
  "LICENSES.md"
 ],
 "sources": [
  {
   "id": "liuhaotian/LLaVA-Pretrain",
   "licence": "other",
   "found": true,
   "evidence": "https://huggingface.co/datasets/liuhaotian/LLaVA-Pretrain/blob/70f9d1e5e1a697fe35830875cfc7de1dd590d727/README.md"
  },
  {
   "id": "ILSVRC/imagenet-1k",
   "licence": "other",
   "found": true,
   "evidence": "https://huggingface.co/datasets/ILSVRC/imagenet-1k/blob/49e2ee26f3810fb5a7536bbf732a7b07389a47b5/README.md"
  }
 ],
 "gated": false,
 "tasks": [
  "image-classification",
  "other"
 ],
 "citation": "@misc{yang2026strong,\n  title={A Strong Baseline for Evaluating Vision Encoders in Multimodal Large Language Models},\n  author={Yang, Yilin and Tang, Jun-Tao and Wang, Kengyi and Su, Siyuan and Luo, Gaoyong and Chen, Mingda},\n  year={2026},\n  eprint={2610.05413},\n  archivePrefix={arXiv},\n  primaryClass={cs.CV},\n  url={https://arxiv.org/abs/2610.05413}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "c8e0e25bad6e576c5cf311460b602e683fc6dd74",
 "stated_evidence": "https://huggingface.co/datasets/336labs/VisionEncoder-Eval-ReproData/blob/c8e0e25bad6e576c5cf311460b602e683fc6dd74/README.md",
 "file_evidence": "https://huggingface.co/datasets/336labs/VisionEncoder-Eval-ReproData/blob/c8e0e25bad6e576c5cf311460b602e683fc6dd74/LICENSES.md",
 "card_nc": false
}