I am currently an undergraduate student in Information Engineering at Shanghai Jiao Tong University, where I will continue my graduate study as a master's student. I am advised by Prof. Guo Lu.
My research interests mainly focus on multimodal LLMs, especially Video-LLMs, full-duplex Audio-LLMs, and token compression, with an emphasis on improving efficiency while preserving strong multimodal understanding performance.
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "News
Selected Publications (view all )
Unified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retention
Junhao Du*, Jialong Xue*, Anqi Li, Jincheng Dai, Guo Lu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026
We formulate token compression for Video-LLMs as a unified spatiotemporal allocation problem under a global retention budget. The method preserves strong video understanding performance at ultra-low token retention without retraining.
Unified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retention
Junhao Du*, Jialong Xue*, Anqi Li, Jincheng Dai, Guo Lu
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026
We formulate token compression for Video-LLMs as a unified spatiotemporal allocation problem under a global retention budget. The method preserves strong video understanding performance at ultra-low token retention without retraining.
All publications
Education
Experience
