About Me
I’m a second-year Ph.D. candidate in Computer Science at University of Illinois Urbana-Champaign, working under the supervision of Hanghang Tong. Prior to this, I earned my bachelor’s degree from the University of Michigan.
My current research interests center on scaling foundation models toward stronger reasoning and agentic capabilities. My past work spans a broad spectrum of post-training, including learning (SFT-loss), judging (RM-R1), and inferencing (JuICE). I am especially drawn to two complementary research styles: (1) conducting deep analysis to uncover new insights that challenge established conventions, and (2) training larger and more capable models through heavy engineering. More recently, I have also become interested in language modeling and new paradigms for model reasoning.
Email: gaotang3 [at] illinois [dot] edu
You can call me as Oliver. If you would like to chat with me about anything (e.g. research, internship opportunities, grad school application, mentorship etc.), feel free to fill out this form. Students from underrepresented groups are especially encouraged to reach out.
Selected Papers
(* denotes equal contribution)
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
Gaotang Li*, Ruizhong Qiu*, Xiusi Chen*, Heng Ji, Hanghang Tong
ICML 2026 (spotlight)
[PDF] [Code] [Tweet]RM-R1: Reward Modeling as Reasoning
Xiusi Chen*, Gaotang Li*, Ziqi Wang*, Bowen Jin, Cheng Qian, Yu Wang, Hongru Wang, Yu Zhang, Denghui Zhang, Tong Zhang, Hanghang Tong, Heng Ji
ICLR 2026
[PDF] [Code] [HuggingFace] [Project Page] [Tweet]
Taming Knowledge Conflicts in Language Models
Gaotang Li, Yuzhong Chen, Hanghang Tong
ICML 2025 (spotlight)
[PDF] [Code] [HuggingFace] [Project Page] [Tweet]Latent Collaboration in Multi-Agent Systems
Jiaru Zou*, Xiyuan Yang*, Ruizhong Qiu, Gaotang Li, Katherine Tieu, Pan Lu, Ke Shen, Hanghang Tong, Yejin Choi, Jingrui He, James Zou, Mengdi Wang, Ling Yang
ICML 2026 (spotlight)
[PDF] [Code] [Tweet]Efficient Inference Scaling for Safety Assurance
Ruizhong Qiu*, Gaotang Li*, Ting-Wei Li*, Tianxin Wei, Jingrui He, Hanghang Tong
NeurIPS Workshop on Vision–Language Model Real-World Deployment, 2025
[PDF] [Code] [Project Page] [Tweet]
