Ziqi Wang (王子奇)

I am a Ph.D. student at the University of Illinois Urbana-Champaign, advised by Prof. Heng Ji and Prof. Tong Zhang. My long-term goal is to develop an AI system that pushes the boundaries of human knowledge.

I interned at Google, Meta, and Yutori during my Ph.D. study, where I was fortunate to be advised by Dr. Crick Wu, Dr. Le Hou and Rui Wang. Before my Ph.D. study, I obtained a Bachelor's Degree in Computer Science at Tsinghua University, where I was fortunate to work with Prof. Zhiyuan Liu, Prof. Xiaolin Hu, Prof. Minlie Huang, and Prof. Xiang Ren at the University of Southern California.

Email  /  Google Scholar  /  Linkedin

profile photo

Selected Publications

* denotes equal contribution.

RM-R1: Reward Modeling as Reasoning
Xiusi Chen*, Gaotang Li*, Ziqi Wang*, And other 9 authors.
Preprint, 2025  
Paper

Reward model with thinking improves the rewards accuracy.

Eliminating Position Bias of Language Models: A Mechanistic Approach
Ziqi Wang, Hanlin Zhang, Xiner Li, Kuan-Hao Huang, Chi Han, Shuiwang Ji, Sham M. Kakade, Hao Peng, Heng Ji
ICLR, 2025  
Paper / Twitter

We propose a method to eliminate the position bias in LMs, which help LMs to better conduct reasoning.

Enabling Language Models to Implicitly Learn Self-Improvement
Ziqi Wang, Le Hou, Tianjian Lu, Yuexin Wu, Yunxuan Li, Hongkun Yu, Heng Ji
ICLR, 2024  
Paper / Slides / Twitter

Teaching models self-improvement with reinforcement learning.

Education

University of Illinois Urbana-Champaign
Ph.D. in Computer Science, 2021-2025

Advisor: Prof. Heng Ji and Prof. Tong Zhang
Tsinghua University
B.E. in Computer Science, 2016-2021

Advisor: Prof. Zhiyuan Liu, Prof. Xiaolin Hu, and Prof. Minlie Huang

The website is adapted from Jon Barron. Last update: Aug, 2025.