mvp-lab/LLaVA-OneVision-2-Data

Tasks

• video-text-to-text
• visual-question-answering
• image-text-to-text

Citation text from the card

@misc{an2026llavaonevision2nextgenerationperceptualintelligence,
  title         = {LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence},
  author        = {Xiang An and Yin Xie and Feilong Tang and Yunyao Yan and Huajie Tan and Didi Zhu and Changrui Chen and Xiuwei Zhao and Bin Qin and Kaicheng Yang and Yifei Shen and Yuanhan Zhang and Kaichen Zhang and Wenkang Zhang and Zheng Cheng and Nansen Zhang and Chunsheng Wu and Chunjiang Ge and Zimin Ran and Dehua Song and Chunyuan Li and Shikun Feng and Ming Hu and Zhangquan Chen and Junbo Niu and Bo Li and Ziyong Feng and Ziwei Liu and Zongyuan Ge and Jiankang Deng},
  year          = {2026},
  eprint        = {2605.25979},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CV},
  url           = {https://arxiv.org/abs/2605.25979}
}

@misc{an2025llavaonevision15fullyopenframework,
  title         = {LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training},
  author        = {Xiang An and Yin Xie and Kaicheng Yang and Wenkang Zhang and Xiuwei Zhao and Zheng Cheng and Yirui Wang and Songcen Xu and Changrui Chen and Didi Zhu and Chunsheng Wu and Huajie Tan and Chunyuan Li and Jing Yang and Jie Yu and Xiyao Wang and Bin Qin and Yumeng Wang and Zizhen Yan and Ziyong Feng and Ziwei Liu and Bo Li and Jiankang Deng},
  year          = {2025},
  eprint        = {2509.23661},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CV},
  url           = {https://arxiv.org/abs/2509.23661}
}

@misc{tang2026onevisi

All datasets marked Permissive or share-alike | JSON