Tansheng Zhu 朱坦晟
About meI am Tansheng Zhu (pronounced Tahn-Shung Joo), a first-year Ph.D. student in the Institute for Interdisciplinary Information Sciences (IIIS) at Tsinghua University. I am grateful to be advised by Prof. Jian Li. I earned my B.S. at Shanghai Jiao Tong University, where I studied in the School of Mathematical Sciences and Zhiyuan College and completed my undergraduate thesis under the mentorship of Prof. Zhenli Xu. During an exchange at The Chinese University of Hong Kong, I was fortunate to join Prof. Fenglei Fan's lab as a research intern. My research interests center on the mathematical foundations of deep learning and large language models. I seek to understand the scaling behavior, optimization process, and implicit biases of neural networks from a mathematical perspective, with particular attention to the interplay between model architecture and training dynamics. I am also interested in statistical learning theory and its applications to modern AI systems. My goal is to develop principled frameworks that not only explain the empirical success of deep learning but also guide the design of more interpretable, reliable, and efficient models. Education
Honors & Awards
|