Hi, I am currently an AI researcher at Huawei Noah’s Ark Lab. I got my Ph.D. degree at UCLA Math Department, advised by Professor Guido Montufar. My research mainly focuses on Large Language Models, Mechanistic Interpretability and Deep Learning Theory. Here is my resume.

Education

  • Ph.D., Department of Mathematics, University of California, Los Angeles, Dec 2022
  • B.S., School of Mathematical Sciences, Peking University, Jul 2017

Publication

Towards understanding how transformer perform multi-step reasoning with matching operation

Zhiwei Wang, Yunji Wang, Zhongwang Zhang, Zhangchen Zhou, Hui Jin, Tianyang Hu, Jiacheng Sun, Zhenguo Li, Yaoyu Zhang, Zhi-Qin John Xu, 2025.

Submitted to The Forty-second International Conference on Machine Learning (ICML 2025).

We propose a buffer mechanism and found evidence that supports such mechanism being employed by language models during the reasoning process. We propose a method to enhance the model’s reasoning capability, significantly improving data utilization efficiency in logical reasoning datasets.

Download [pdf].

Teaching

2020 Fall: PIC 10B Intermediate Programming

Undergraduate course, UCLA, 2020

Abstract data types and their implementation using C++ class mechanism; dynamic data structures, including linked lists, stacks, queues, trees, and hash tables; applications; object-oriented programming and software reuse; recursion; algorithms for sorting and searching.