🚀

Wenjie Shu

(he/him)

Researcher

2077 AI (Nonprofit Organization)

Professional Summary

Wenjie Shu is a researcher at 2077 AI, a nonprofit organization. He previously served as a research assistant and visiting student at the Hong Kong University of Science and Technology (HKUST), working with Prof. Harry Yang and Prof. Qifeng Chen. He earned his B.E. from the University of Electronic Science and Technology of China (UESTC) in 2025 and worked closely with Prof. Liangjian Deng during his undergraduate studies. He has been fortunate to collaborate with Dr. Xiaogang Xu and Dr. Rui-Jie Zhu. His collaborators also include Tim G. J. Rudner, Xianghong Fang, and Dehan Kong.

He is always open to research collaborations and is currently applying to PhD programs, actively seeking opportunities for the next intake. Feel free to get in touch if you are interested in working with him!

Download CV

Education

B.E. in Information Engineering

University of Electronic Science and Technology of China (UESTC)

Visiting Student, Generative AI

The Hong Kong University of Science and Technology (HKUST)

Visiting Student, Video Generation

The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen)

Interests

Image/Video Generation Benchmarking Agents & Recursive Self-Improvement (RSI)

My Research

I study how generative models and agents can reason, solve problems, and improve. My research spans three areas:

Image & Video Generation. Developing generative models with stronger visual reasoning, greater controllability, and efficient training and inference.

Visual Reasoning Benchmarks. Measuring how well generative models understand, reason about, and solve visual problems.

Agents & Recursive Self-Improvement. Exploring how agents can improve their reasoning and decision-making through interaction and feedback.

I actively collaborate across academia and industry. If you’re interested in collaboration, feel free to reach out.

Featured Publications