{
 "id": "FudanCVL/AVIBench",
 "owner": "FudanCVL",
 "name": "AVIBench",
 "downloads": 574,
 "likes": 1,
 "last_modified": "2026-05-28T07:38:32.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "avi-bench-data-use-policy-v1",
 "licence_link": "https://github.com/FudanCVL/AVI-Bench/blob/main/DATA_USE_POLICY.md",
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "auto",
 "tasks": [
  "audio-classification",
  "image-classification",
  "video-classification",
  "visual-question-answering",
  "audio-text-to-text",
  "video-text-to-text",
  "image-text-to-text",
  "any-to-any"
 ],
 "citation": "@inproceedings{wang2026avibench,\n  title     = {AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs},\n  author    = {Wang, Yaoting and Zhang, Ziyi and Tu, Wenming and Xu, Shaoxuan and Du, Wenjie and Liang, Cheng and Wang, Weijun and Li, Yuanchao and Li, Guangyao and Fei, Hao and Li, Yuanchun and Ding, Henghui and Liu, Yunxin},\n  booktitle = {Proceedings of the 43rd International Conference on Machine Learning (ICML)},\n  year      = {2026}\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "27c84e76f76ba2c78d8fefed376d0893509146ac",
 "stated_evidence": "https://huggingface.co/datasets/FudanCVL/AVIBench/blob/27c84e76f76ba2c78d8fefed376d0893509146ac/README.md",
 "file_evidence": "https://huggingface.co/datasets/FudanCVL/AVIBench/tree/27c84e76f76ba2c78d8fefed376d0893509146ac",
 "card_nc": false
}