{
 "id": "CodeGoat24/VideoDPO",
 "owner": "CodeGoat24",
 "name": "VideoDPO",
 "downloads": 151,
 "likes": 0,
 "last_modified": "2025-09-03T07:33:53.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@article{unifiedreward-think,\n  title={Unified multimodal chain-of-thought reward model through reinforcement fine-tuning},\n  author={Wang, Yibin and Li, Zhimin and Zang, Yuhang and Wang, Chunyu and Lu, Qinglin and Jin, Cheng and Wang, Jiaqi},\n  journal={arXiv preprint arXiv:2505.03318},\n  year={2025}\n}\n\n@article{unifiedreward,\n  title={Unified reward model for multimodal understanding and generation},\n  author={Wang, Yibin and Zang, Yuhang and Li, Hao and Jin, Cheng and Wang, Jiaqi},\n  journal={arXiv preprint arXiv:2503.05236},\n  year={2025}\n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "39a557ee8f69dbc7da98d83c49c32427d91967d3",
 "stated_evidence": "https://huggingface.co/datasets/CodeGoat24/VideoDPO/blob/39a557ee8f69dbc7da98d83c49c32427d91967d3/README.md",
 "file_evidence": "https://huggingface.co/datasets/CodeGoat24/VideoDPO/tree/39a557ee8f69dbc7da98d83c49c32427d91967d3",
 "card_nc": false
}