About Me
Hello! I am Zhenglin Cheng, a senior undergraduate student at Zhejiang University (ZJU). I am also an incoming Ph.D. student at
LINs lab, Westlake University (through joint program with ZJU), advised by Prof. Tao LIN.
I love to write ✍️ and post 📬 something (from technical notes to life stuff), I also practice Chinese traditional calligraphy to relax occasionally.
Research Interests
My research interests are generally within the scope of efficiency of AI systems (such as large language models), specifically in model architectural optimization, training accelerating techniques, and deploying / inference paradigms. Still exploring! 🙌
Publications/Manuscripts
![sym](images/adaptive.jpg)
📖 Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models
Yongxin Guo*, Zhenglin Cheng*, Xiaoying Tang, Tao Lin
👉 DynMoE enables each token to automatically determine the number of experts to activate and automatically adjusts the number of experts during training.
News
- 2024/06: 🔮 Successfully defended my undergraduate thesis, ready to graduate!
Educations
- 2020/09 - 2024/06, Zhejiang University, College of Computer Science and Technology.