Zhaowei Zhang(张钊为)

Ph.D. Student
School of Intelligence Science and Technology
Peking University
Email: zwzhang [at] stu (dot) pku (dot) edu (dot) cn

[Google Scholar] [Github]

Zhaowei is pronounced as "Ju" (as in judge) + "ou" (as in out) + "Way", Zhang is "Ju" (as in judge) + "on" | audio ([International Phonetic Alphabet, IPA]) here: [tʂɑuwei][tʂɑŋ].

Research Topics
  • AI Alignment and Interaction
  • Multi-Agent System
  • Scalable Oversight
  • LLMs and Foundation Models
  • Socio-Technical Theory
  • Game Theory and Mechanism Design

I am currently a Ph.D. Student at School of Intelligence Science and Technology, Peking University as well as a research intern at BIGAI. I am in the group of PAIR-Lab led by Prof. Yaodong Yang. The long-term goal of my research is to find a way to build a trustworthy and social AI system. To this end, my research focuses on AI Alignment and Multi-Agent System. In particular, I am currently interested in exploring the potential of the value learning and reward gaming problem for creating an intelligent agent free from utilitarianism (i.e. being only motivated by reward modeling), especially in complex scenarios such as social interaction.

Before entering PKU, I was a Bachelor Student at Wuhan University majoring in Computer Science and Technology. I received the B.E. degree from School of Computer Science at Wuhan University in 2023.

Publications (* indicates equal contribution.)

    2024
  • Incentive Compatibility for AI Alignment in Sociotechnical Systems: Positions and Prospects
    Zhaowei Zhang, Fengshuo Bai, Mingzhi Wang, Haoyang Ye, Chengdong Ma, Yaodong Yang
    Preprint
    [Paper] [Chinese Blog]
  • CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents
    Siyuan Qi, Shuo Chen, Yexin Li, Xiangyu Kong, Junqi Wang, Bangcheng Yang, Pring Wong, Yifan Zhong, Xiaoyuan Zhang, Zhaowei Zhang, Nian Liu, Wei Wang, Yaodong Yang, Song-Chun Zhu
    ICLR 2024 (Spotlight)
    [Paper] [Website] [Code]
  • 2023
  • AI Alignment: A Comprehensive Survey
    PAIR-Lab
    [Paper] [Website]
  • Measuring Value Understanding in Language Models through Discriminator-Critique Gap
    Zhaowei Zhang, Fengshuo Bai *, Jun Gao *, Yaodong Yang
    Preprint
    [Paper] [Blog]
  • ProAgent: Building Proactive Cooperative AI with Large Language Models
    Ceyao Zhang, Kaijie Yang, Siyi Hu, Zihao Wang, Guanghe Li, Yihang Sun, Cheng Zhang, Zhaowei Zhang, Anji Liu, Song-Chun Zhu, Xiaojun Chang, Junge Zhang, Feng Yin, Yitao Liang, Yaodong Yang
    AAAI 2024 (Oral)
    [Paper]
  • Heterogeneous Value Alignment Evaluation for Large Language Models
    Zhaowei Zhang, Nian Liu, Siyuan Qi, Ceyao Zhang, Ziqi Rong, Shuguang Cui, Song-Chun Zhu, Yaodong Yang
    AAAI 2024 Workshop: Public Sector LLMs (Oral)
    [Paper]
  • STAS: Spatial-Temporal Return Decomposition for Multi-agent Reinforcement Learning
    Sirui Chen *, Zhaowei Zhang *, Yali Du, Yaodong Yang
    AAAI 2024
    [Paper] [Code]
  • 2022
  • Contextual Transformer for Offline Meta Reinforcement Learning
    Runji Lin, Ye Li, Xidong Feng, Zhaowei Zhang, Xian Hong Wu Fung, Haifeng Zhang, Jun Wang, Yali Du, Yaodong Yang
    FMDM Workshop at NeurIPS 2022
    [Paper]

Selected Awards

  • [Top 5%] Wuhan University Outstanding Thesis Award. 2023