Hi! I am Wei Dai (戴维). I received my B.S. in Data Science from the University of Science and Technology of China (USTC) in 2026. I am an incoming Ph.D. student at the School of Computing and Data Science at The University of Hong Kong (HKU), starting in Fall 2026, where I will be advised by Prof. Dong Xu.

My research focuses on world models. In particular, I am interested in improving their memory mechanisms and consistency, as well as developing dynamic 4D world models.

Research Interests

• World models
• Memory and consistency in world models
• Dynamic 4D world models

Research Experience

My research journey began in Prof. Zhenya Huang’s group at USTC. I later had a wonderful experience as a visiting student in Prof. Long Chen’s group at The Hong Kong University of Science and Technology (HKUST).

Recent Work

• Verifying Large Language Models’ Reasoning Paths via Correlation Matrix Rank. Jiayu Liu, Wei Dai, Zhenya Huang, Ning Miao, and Enhong Chen. arXiv, 2025. [Paper]
• CogMath: Assessing LLMs’ Authentic Mathematical Ability from a Human Cognitive Perspective. Jiayu Liu, Zhenya Huang, Wei Dai, Cheng Cheng, Jinze Wu, Jing Sha, Song Li, Qi Liu, Shijin Wang, and Enhong Chen. ICML, 2025. [Paper] [arXiv]

For a complete list, please visit the Publications page or my Google Scholar profile.

Contact

The best way to reach me is by email at david21@mail.ustc.edu.cn.