{
 "id": "nvidia/av-skills",
 "owner": "nvidia",
 "name": "av-skills",
 "downloads": 604,
 "likes": 9,
 "last_modified": "2026-07-22T18:11:06.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "video-text-to-text"
 ],
 "citation": "@misc{ghosh2026audiovisualflamingoopenaudiovisual,\n      title={Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos}, \n      author={Sreyan Ghosh and Arushi Goel and Kaousheik Jayakumar and Lasha Koroshinadze and Nishit Anand and Siddharth Gururani and Hanrong Ye and Pritam Biswas and Yuanhang Su and Ehsan Hosseini-Asl and Sang-gil Lee and Zhifeng Kong and Jaehyeon Kim and Sungwon Kim and S Sakshi and Ramani Duraiswami and Dinesh Manocha and Andrew Tao and Mohammad Shoeybi and Bryan Catanzaro and Ming-Yu Liu and Wei Ping},\n      year={2026},\n      eprint={2607.16107},\n      archivePrefix={arXiv},\n      primaryClass={eess.AS},\n      url={https://arxiv.org/abs/2607.16107}, \n}",
 "signal": "restrictive",
 "reason": "The dataset card's licence name or licence section contains wording that suggests non-commercial, research-only or academic-only use restrictions.",
 "revision": "4429e34ee80f4fe13de31b5c8def4d86c4f0daa2",
 "stated_evidence": "https://huggingface.co/datasets/nvidia/av-skills/blob/4429e34ee80f4fe13de31b5c8def4d86c4f0daa2/README.md",
 "file_evidence": "https://huggingface.co/datasets/nvidia/av-skills/tree/4429e34ee80f4fe13de31b5c8def4d86c4f0daa2",
 "card_nc": true
}