Published several papers, including but not limited to 'Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL' (NeurIPS 2025), 'Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods' (ICML 2024). Also serves as a reviewer for top conferences such as NeurIPS, ICML, ICLR, AISTATS, AAAI, and journals like Journal of Machine Learning Research, SIAM Journal on Mathematics of Data Science.
Research Experience
No specific work experience or research projects are mentioned.
Education
Master's degree in mathematics from The Hong Kong University of Science and Technology in 2024; B.S. in Statistics from the University of Science and Technology of China in 2022; currently a second-year Ph.D. student in Computer Science at UIUC, advised by Prof. Tong Zhang.
Background
Research Interests: At the intersection of machine learning and statistics, particularly interested in developing efficient algorithms for modern machine learning systems (such as large language models) and exploring the theoretical foundations that explain their effectiveness.
Miscellany
Can be contacted via email: yifanh12 AT Illinois DOT edu or yhaoah AT connect AT ust AT hk.