Lai Jiang

prof_pic.jpg

I am an MSCS student at the University of Illinois Urbana-Champaign (UIUC), where I am fortunate to have the opportunity to learn from and conduct research with Prof. Hao Peng and Prof. Heng Ji. Previously, I worked as a Research Assistant at Princeton PLI, advised by Prof. Chi Jin where my work focused on autonomous theorem proving with LLMs (Check out our Goedel-Prover-V2 🙌).

I obtained my B.S. from Shanghai Jiao Tong University, where I was a member of the ACM Honors Class. During my undergraduate studies, I was fortunate to work on research projects under the supervision of Prof. Lianhui Qin at UCSD and Prof. Hai Zhao at SJTU.

My research focuses on developing next-generation LLM reasoning systems with enhanced creativity, accuracy, and generalization through improved training and data synthesis methods.

News

May 2025 Flow of Reasoning has been accepted to ICML 2025! Check it out :sparkles:

Publications & Preprints

  1. Goedel-Prover-V2.png
    Goedel-Prover-V2: The Strongest Open-Source Theorem Prover to Date
    Yong Lin*, Shange Tang*, Bohan Lyu*, Ziran Yang*, Jui-Hui Chung*, Haoyu Zhao*, Lai Jiang*, Yihan Geng*, and 11 more authors
    AI4MATH@ICML 2025 (Oral)
  2. ICML
    FoR.png
    Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples
    Fangxu Yu*, Lai Jiang*, Haoqiang Kang*, Shibo Hao, and Lianhui Qin
    ICML 2025
  3. ACL Findings
    D2C.png
    Chinese Spelling Corrector Is Just a Language Learner
    Lai Jiang*, Hongqiu Wu*, Hai Zhao, and Min Zhang
    In Findings of the Association for Computational Linguistics: ACL 2024
  4. ICLR Workshop
    sou.png
    Understanding the Sources of Uncertainty for Large Language and Multimodal Models
    Ziran Yang, Shibo Hao, Hao Sun, Lai Jiang, Qiyue Gao, Yian Ma, and Zhiting Hu
    In ICLR Workshop: Quantify Uncertainty and Hallucination in Foundation Models: The Next Frontier in Reliable AI , 2025
  5. ACL Findings
    Drama.png
    From Role-Play to Drama-Interaction: An LLM Solution
    Weiqi Wu*, Hongqiu Wu*, Lai Jiang, Xingyuan Liu, Hai Zhao, and Min Zhang
    In Findings of the Association for Computational Linguistics: ACL 2024