I am the first-year PhD student in CSE, HKUST, advised by Prof. Song Guo. I am now working on multimodal LLM, video understanding.

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, video/image enhancement, and time series forecasting. I am maintaining a popular repository of papers on time series forecasting .

🔥 News

• 2025.11: 🎉 One paper is accepted by AAAI 2026
• 2025.09: 🎉 One paper is accepted by Neural Networks
• 2024.09: 🎉 One paper is accepted by Expert Systems with Applications
• 2023.04: 🎉 One paper is accepted by IJCAI 2023
• 2023.03: 🎉 One paper is accepted by ICME 2023
• 2023.02: 🎉 One paper is accepted by ICASSP 2023

📝 Publications

🎥 Video Understanding

• IJCAI 2023 (CCF A) Timestamp-Supervised Action Segmentation from the Perspective of Clustering, Dazhao Du, Enhan Li, Lingyu Si, Fanjiang Xu^✉, Fuchun Sun |
• ICME 2023 (CCF B, Oral) Do we really need temporal convolutions in action segmentation, Dazhao Du, Bing Su^✉, Yu Li, Zhongang Qi, Lingyu Si, Ying Shan |
• ICTAI 2022 (CCF C) Convolutional Transformer with Similarity-based Boundary Prediction for Action Segmentation, Dazhao Du, Bing Su^✉, Yu Li, Zhongang Qi, Lingyu Si, Ying Shan.

🌊 Underwater Video/Image Enhancement

• ESWA 2024 (CCF C, JCR Q1, IF=7.5) UIEDP: Boosting Underwater Image Enhancement with Diffusion Prior, Dazhao Du, Enhan Li, Lingyu Si, Wenlong Zhai, Fanjiang Xu^✉, Jianwei Niu, Fuchun Sun.
• Arxiv 2024 A Physical Model-Guided Framework for Underwater Image Enhancement and Depth Estimation, Dazhao Du, Lingyu Si, Fanjiang Xu^✉, Jianwei Niu, Fuchun Sun.
• NN 2025(CCF B, JCR Q1, IF=6.3) UVENet: A Novel End-to-End Model for Temporal Consistency in Underwater Video Enhancement, Huijie Guo, Dazhao Du, Hongwei Dong, Shouyou Huang, Changwen Zheng, Lingyu Si^✉.

📈 Time Series Forecasting

• AAAI 2026 (CCF A) Predicting the Future by Retrieving the Past, Dazhao Du, Tao Han, Song Guo^✉.
• ICASSP 2023 (CCF B) Preformer: predictive transformer with multi-scale segment-wise correlations for long-term time series forecasting, Dazhao Du, Bing Su^✉, Zhewei Wei |

Others

• Arxiv 2022 A molecular multimodal foundation model associating molecule graphs with natural language, Bing Su, Dazhao Du, Zhao Yang, Yujie Zhou, Jiangmeng Li, Anyi Rao, Hao Sun, Zhiwu Lu, Ji-Rong Wen^✉ |

🥇 Honors and Awards

• 2022.10, National Scholarship, University of Chinese Academy of Sciences
• 2022.10, Merit student, University of Chinese Academy of Sciences
• 2021.10, Merit student, University of Chinese Academy of Sciences

📖 Educations

• 2016.08 - 2020.06, Undergraduate, Department of Automation, Tsinghua University, Beijing.
• 2020.08 - 2023.06, Master, Institute of Software, University of Chinese Academy of Sciences, Beijing.
• 2025.08 - Now, PhD, Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hongkong.

💻 Internships

• 2022.07 - 2022.11, ByteBrain, ByteDance, Beijing.

👨‍💻 Academic Services

• Conference Reviewer: NeurIPS 2023/2025, ICLR 2024/2025/2026, ICASSP 2024
• Journal Reviewer: Transactions on Image Processing, IEEE Transactions on Circuits and Systems for Video Technology, Neural Networks, Machine Vision and Applications