Cite
Notes
Only stored in your browser.
Attribution
TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions
arXiv 2026
Innovator-VL: A Multimodal Large Language Model for Scientific Discovery
from 2 papers
Boxue Yang
Cong Wang
Feifan Song
Feiyu Xiong
Guojiang Zhao
Guolin Ke
Han Lyu
Haoyi Tao
Henxing Cai
Jiangchao Yao