{
 "id": "tic26/VTOS-Bench",
 "owner": "tic26",
 "name": "VTOS-Bench",
 "downloads": 77,
 "likes": 0,
 "last_modified": "2026-10-30T05:16:00.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "object-detection",
  "image-segmentation",
  "visual-question-answering"
 ],
 "citation": "@inproceedings{ge2026vtos,\n  title     = {{VTOS}: Learning to Orchestrate Vision Tools by Co-Searching Solutions and Observers},\n  author    = {Ge, Jinchao and Liu, Lingqiao and Zhao, Shuwen and Wang, Lei},\n  booktitle = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing},\n  month     = oct,\n  year      = {2026},\n  address   = {Budapest, Hungary},\n  publisher = {Association for Computational Linguistics},\n  url       = {https://aclanthology.org/2026.emnlp-main.977/},\n  pages     = {22551--22569},\n  ISBN      = {979-8-89176-459-0}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "8cf34426fc766edb396600745d112698de85117a",
 "stated_evidence": "https://huggingface.co/datasets/tic26/VTOS-Bench/blob/8cf34426fc766edb396600745d112698de85117a/README.md",
 "file_evidence": "https://huggingface.co/datasets/tic26/VTOS-Bench/tree/8cf34426fc766edb396600745d112698de85117a",
 "card_nc": false
}