Yuanhan Zhang*, Yunice Chew*, Yuhao Dong, Aria Leo, Bo Hu, Ziwei Liu
A holistic benchmark to assess advanced reasoning and understanding correctness/robustness between MLLMs and humans.
Yuanhan Zhang, Jinming Wu, Wei Li, Bo Li, Zejun Ma, Ziwei Liu, Chunyuan Li
Fully open-sourced video LMM (code, model, and data) with competitive ability.
Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Yanwei Li, Ziwei Liu, Chunyuan Li
A family of LMMs consolidating insights into data, models, and visual representations.
Yuan Liu*, Haodong Duan*, Yuanhan Zhang*, Bo Li*, Songyang Zhang*, Wangbo Zhao, Yike Yuan, Jiaqi Wang, Conghui He, Ziwei Liu, Kai Chen, Dahua Lin
Benchmarking 20 abilities of vision-language models.
Bo Li*, Yuanhan Zhang*, Liangyu Chen, Jinghao Wan, Fanyi Pu, Jingkang Yang, Chunyuan Li, Ziwei Liu
A vision-language model with in-context instruction tuning.
Yuanhan Zhang, Kaiyang Zhou, Ziwei Liu
Searching prompt modules for parameter-efficient transfer learning.
Yuanhan Zhang, Qinghong Sun, Yichun Zhou, Zexin He, Zhenfei Yin, Kun Wang, Lv Sheng, Yu Qiao, Jing Shao, Ziwei Liu
4x larger than ImageNet, 2x larger than Object365 — built by active learning.
Yuanhan Zhang, Kaiyang Zhou, Ziwei Liu
Retrieving prompts for visual in-context learning.
Yuanhan Zhang, Zhenfei Yin, Jing Shao, Ziwei Liu
New benchmark for evaluating vision foundation models; supervised contrastive learning framework.
