Xiangrui Liu (刘祥睿)

HKU MMLab Lumina

Undergraduate Student @ Beijing University of Chemical Technology

Research Intern @ Beijing Academic of Artificial Intelligence

Email   Google Scholar   WeChat   Xiaohongshu  

Profile Photo

Biography

Hello, I am Xiangrui Liu, a senior undergraduate student at Beijing University of Chemical Technology, I am currently working as a research intern at Beijing Institute of Artificial Intelligence, supervised by Prof. Zheng Liu, and previously served as a research intern at Shanghai Jiao Tong University under the supervision of Prof. Bo Zhao. I am dedicated to exploring Video MLLM, especially long video understanding, temporal understanding, and spatial understanding.

News

⬆ scrollable

Publications | [My Google Scholar]

Full List
TimeScope: Towards Task-Oriented Temporal Grounding In Long Videos
Xiangrui Liu*, Minghao Qin*, Yan Shu, Zhengyang Liang, Yang Tian, Chen Jason Zhang, Bo Zhao, Zheng Liu
Under Review
Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification
Minghao Qin*, Xiangrui Liu*, Zhengyang Liang*, Yan Shu, Huaying Yuan, Juenjie Zhou, Shitao Xiao, Bo Zhao, Zheng Liu
Technical Report
STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?
Yun Li, Yiming Zhang, Tao Lin, Xiangrui Liu, Wenxiao Cai, Zheng Liu, Bo Zhao
ICCV2025
Video-XL-Pro: Reconstructive Token Compression for Extremely Long Video Understanding
Xiangrui Liu*, Yan Shu*, Zheng Liu*, Ao Li, Yang Tian, Bo Zhao
Under Review

Latest updated in 2025.10

© Xiangrui Liu