I am a Ph.D. student in Computer Science at Brigham Young University (BYU), advised by Prof. Porter Jenkins, and I also collaborate with Prof. Weitong Zhang (UNC). I received my M.S. from Penn State (IST), where I was advised by Prof. Fenglong Ma (PSU), and I earned my B.S. in Mathematics from Shenzhen University.

My early work focused on fairness in federated learning. Recently, my primary research direction has moved to LLM reasoning, with a focus on post-training and test-time scaling (TTS). I am always happy to connect and discuss related ideas.

🔥 News

2026.01: 🎉 One paper was accepted to ICLR 2026.

📝 Publications

LLM Reasoning

Provable and Practical In-Context Policy Optimization for Self-Improvement
Tianrun Yu, Yuxiao Yang, Zhaoyang Wang, Kaixiang Zhao, Porter Jenkins, Xuchao Zhang, Chetan Bansal, Huaxiu Yao, Weitong Zhang
ICLR 2026
PDF

Federated Learning

Towards Collaborative Fairness in Federated Learning Under Imbalanced Covariate Shift
Tianrun Yu, Jiaqi Wang, Haoyu Wang, Mingquan Lin, Han Liu, Nelson S. Yee, Fenglong Ma
KDD 2025
PDF
When the Server Steps In: Calibrated Updates for Fair Federated Learning
Tianrun Yu, Kaixiang Zhao, Cheng Zhang, Anjun Gao, Yueyang Quan, Zhuqing Liu, Minghong Fang
WiOpt 2026
PDF

🎖 Honors and Awards

2023: National Scholarship of China
2022: Mathematical Contest in Modeling (MCM/ICM), Honorable Mention (F Award)
2021: Shenzhen University Top-notch Innovative Talents Scholarship

📖 Educations

2026.01 - Present, Ph.D. in Computer Science, Brigham Young University
2024.09 - 2025.12, M.S. in Informatics, The Pennsylvania State University
2020.09 - 2024.07, B.S. in Mathematics, Shenzhen University