{
 "id": "OpenGVLab/V2PE-Data",
 "owner": "OpenGVLab",
 "name": "V2PE-Data",
 "downloads": 3558,
 "likes": 8,
 "last_modified": "2024-12-14T06:55:49.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "visual-question-answering",
  "question-answering"
 ],
 "citation": "If you find this work helpful in your research, please consider citing:\n\n```bibtex\n@misc{ge2024v2peimprovingmultimodallongcontext,\n      title={V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding}, \n      author={Junqi Ge and Ziyi Chen and Jintao Lin and Jinguo Zhu and Xihui Liu and Jifeng Dai and Xizhou Zhu},\n      year={2024},\n      eprint={2412.09616},\n      archivePrefix={arXiv},\n      primaryClass={cs.CV},\n      url={https://arxiv.org/abs/2412.09616}, \n}\n``",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "69fb61883029e733ae90514b682b981c25ffa7b6",
 "stated_evidence": "https://huggingface.co/datasets/OpenGVLab/V2PE-Data/blob/69fb61883029e733ae90514b682b981c25ffa7b6/README.md",
 "file_evidence": "https://huggingface.co/datasets/OpenGVLab/V2PE-Data/tree/69fb61883029e733ae90514b682b981c25ffa7b6",
 "card_nc": false
}