CG-Bench helps machines analyze long videos better with clue-based questions.
Guo Chen, Yicheng Liu, Yifei Huang
― 6 min read
Yali Wang
New method boosts multimodal language models' visual task performance.
Ziang Yan, Zhilin Li, Yinan He
― 6 min read
Vinci makes daily tasks easier with hands-free help and real-time guidance.
Yifei Huang, Jilan Xu, Baoqi Pei
― 7 min read