About
I am a first-year PhD student at CSE, HKUST, advised by Prof. Song Guo. I am a member of the Pervasive Intelligence Lab.
Prior to this, I graduated from Department of Automation, Tsinghua University (清华大学自动化系) with a bachelor's degree and from the Institute of Software Chinese Academy of Science, University of Chinese Academy of Sciences (中科院软件所) with a master's degree, advised by Prof. Bing Su and Prof. Fanjiang Xu. After graduating from UCAS, I worked at Hangzhou Innovation Institute of Beihang University.
My research interest includes multimodal LLM, video understanding, spatial intelligence, video/image enhancement, and time series forecasting. I am maintaining a popular repository of papers on time series forecasting TSFpaper.
News
One co-authored paper has been accepted by ICML 2026 🎉
One co-authored paper has been accepted by CVPR 2026 🎉
One paper has been accepted by IEEE TCSVT 🎉
One paper has been accepted by AAAI 2026 🎉
Starting my PhD at the Hong Kong University of Science and Technology
One paper has been accepted by Neural Networks 🎉
One paper has been accepted by Expert Systems with Applications 🎉
One paper has been accepted by IJCAI 2023 🎉
Selected Publications
View All →Learning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning
Dazhao Du, Jian Liu, Jialong Qin, Tao Han, Bohai Gu, Fangqi Zhu, Yujia Zhang, Eric Liu, Xi Chen, Song Guo✝
arXiv preprint arXiv:2605.21988
MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues
Dazhao Du✦, Liao Duan✦, Jian Liu, Tao Han, Yujia Zhang, Eric Liu, Xi Chen, Song Guo✝
arXiv preprint arXiv:2605.21954
A physical model-guided framework for underwater image enhancement and depth estimation
Dazhao Du, Lingyu Si, Fanjiang Xu✝, Jianwei Niu, Fuchun Sun
IEEE Transactions on Circuits and Systems for Video Technology
Predicting the Future by Retrieving the Past
Dazhao Du, Tao Han, Song Guo✝
The 40th Annual AAAI Conference on Artificial Intelligence (AAAI)