portrait.png
Be in touch with me at
[email protected]

Jibang Wu

I am a PhD student at the Sigma Lab@UChicago, advised by Prof. Haifeng Xu. Prior to UChicago, I received my BA/MS degrees in CS from UVA in 2019, where I worked on recommendation algorithms with Prof. Hongning Wang.

My current research lies at the interface between game theory, learning theory and optimization, with the primary focus on modeling and solving multi-agent decision-making problems under complex, unknown environment. More broadly, I aim to advance the design principles and approaches of intelligent systems towards strategic alignment — a concept centered on aligning the interests of all stakeholders to achieve mutually beneficial outcomes.

Towards this end, I am interested in developing practical techniques to 1) build incentive-aware AI agents with strategic intelligence and rationalizable behaviors; 2) align the economic incentives of users, model developers and data providers for more sustainable AI ecosystems.

I am on the academic job market 2024-2025.

My CV can be found here. Let’s connect and chat!


Publications

(α-β) indicates alphabetical author order, Ⓡ indicates randomized author order, * indicates equal contribution

  1. Grounded Persuasive Language Generation for Automated Marketing
    Jibang Wu, Chenghao Yang, Simon Mahns, Chaoqi Wang, Hao Zhu, Fei Fang, and Haifeng Xu
    Working Paper
  2. Contractual Reinforcement Learning: Pulling Arms with Invisible Hands
    Jibang Wu, Siyu Chen, Mengdi Wang, Huazheng Wang, and Haifeng Xu
    Working Paper
  3. A Truth Serum for Eliciting Self-Evaluations in Scientific Reviews
    Jibang Wu, Haifeng Xu, Yifan Guo, and Weijie Su
    Working Paper
  4. Auctioning with Strategically Reticent Bidders
    Jibang Wu, Ashwinkumar Badanidiyuru, and Haifeng Xu
    WINE 2024
  5. Generalized Principal-Agency: Contracts, Information, Games and Beyond
    (α-β) Jiarui Gan, Minbiao Han, Jibang Wu, and Haifeng Xu
    WINE 2024
  6. Robust Stackelberg Equilibria
    (α-β) Jiarui Gan, Minbiao Han, Jibang Wu, and Haifeng Xu
    EC 2023
  7. Learning to Incentivize Information Acquisition: Proper Scoring Rules Meet Principal-Agent Model
    Siyu Chen, Jibang Wu, Yifan Wu, and Zhuoran Yang
    ICML 2023
  8. Inverse Game Theory for Stackelberg Games: the Blessing of Bounded Rationality
    Jibang Wu, Weiran Shen, Fei Fang, and Haifeng Xu
    NeurIPS 2022
  9. Sequential Information Design: Markov Persuasion Process and Its Efficient Reinforcement Learning
    Jibang Wu, Zixuan Zhang, Zhe Feng, Zhaoran Wang, Zhuoran Yang, Michael I. Jordan, and Haifeng Xu
    EC 2022
  10. Multi-Agent Learning for Iterative Dominance Elimination: Formal Barriers and New Algorithms
    Jibang Wu, Haifeng Xu, and Fan Yao
    COLT 2022
  11. Least square calibration for peer reviews
    Sijun Tan*, Jibang Wu*, Xiaohui Bei, and Haifeng Xu
    NeurIPS 2021
  12. Category-aware collaborative sequential recommendation
    Renqin Cai, Jibang Wu, Aidan San, Chong Wang, and Hongning Wang
    SIGIR 2021
  13. Déjà vu: A contextualized temporal attention mechanism for sequential recommendation
    Jibang Wu, Renqin Cai, and Hongning Wang
    WWW 2020