Publications

2024

  1. octopus.jpg
    Octopus: Embodied Vision-Language Programmer from Environmental Feedback
    Jingkang Yang*, Yuhao Dong*, Shuai Liu*, Bo Li*, Ziyue Wang, Chencheng Jiang, Haoran Tan, Jiamu Kang, Yuanhan Zhang, Kaiyang Zhou, and Ziwei Liu
    2024
    arXiv HTML Video Code
  2. lmms-eval.png
    LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models
    Kaichen Zhang, Bo Li, Peiyuan Zhang, Fanyi Pu, Joshua Adrian Cahyono, Kairui Hu, Shuai Liu, Yuanhan Zhang, Jingkang Yang, Chunyuan Li, and Ziwei Liu
    2024
    arXiv Blog Code Website
  3. lmms-eval-vid.png
    Embracing Video Evaluations with LMMs-Eval
    Kairui Hu*, Fanyi Pu*, Kaichen Zhang*, Shuai Liu*, Yuanhan Zhang*, Bo Li*, Peiyuan Zhang, and Ziwei Liu
    2024
    Blog

2023

  1. psg4d.png
    4D Panoptic Scene Graph Generation
    Jingkang Yang, Jun Cen, Wenxuan Peng, Shuai Liu, Fangzhou Hong, Xiangtai Li, Kaiyang Zhou, Qifeng Chen, and Ziwei Liu
    2023
    arXiv Code