{
 "id": "ali-vosoughi/ave-2",
 "owner": "ali-vosoughi",
 "name": "ave-2",
 "downloads": 39,
 "likes": 4,
 "last_modified": "2026-10-02T01:47:54.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "manual",
 "tasks": [
  "audio-classification",
  "video-classification",
  "other"
 ],
 "citation": "@inproceedings{vosoughi2025avva,\r\n  title={Quality Over Quantity? LLM-Based Curation for a Data-Efficient Audio-Video Foundation Model},\r\n  author={Vosoughi, Ali and Emmanouilidou, Dimitra and Gamper, Hannes},\r\n  booktitle={33rd European Signal Processing Conference (EUSIPCO)},\r\n  year={2025}\r\n}\r\n\r\n@unpublished{vosoughi2026soundclip,\r\n  title={Projected Audio Tokens Gain Retrieval and Lose Grounded Generation in Multimodal LLMs},\r\n  author={Vosoughi, Ali and Bi, Jing and Liu, Pinxin and Tang, Yolo Y. and Xu, Chenliang},\r\n  year={2026},\r\n  note={Preprint; submitted to ICASSP 2027. Project page: https://ali-vosoughi.github.io/SoundCLIP/}\r\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "d88d7d988de62c6d2f0d6a213a703641207b2a58",
 "stated_evidence": "https://huggingface.co/datasets/ali-vosoughi/ave-2/blob/d88d7d988de62c6d2f0d6a213a703641207b2a58/README.md",
 "file_evidence": "https://huggingface.co/datasets/ali-vosoughi/ave-2/tree/d88d7d988de62c6d2f0d6a213a703641207b2a58",
 "card_nc": false
}