Yifan Hao

Ph.D. student University of Illinois Urbana-Champaign, Computer Science [Curriculum Vitae]      [Google Scholar] Email: yifanh12 AT Illinois DOT edu

I am a second-year Ph.D. student in computer science at UIUC, where I am fortunate to advised by Prof. Tong Zhang. Previously, I obtained a master's degree in mathematics in 2024 at The Hong Kong University of Science and Technology, where my study was supported by the Hong Kong PhD Fellowship. Before that, I received a B.S. in Statistics from the University of Science and Technology of China in 2022.

Research Interests

My research interests lie at the intersection of machine learning and statistics. I am particularly interested in developing efficient algorithms for modern machine learning systems (such as large language models) and in exploring the theoretical foundations that explain their effectiveness.

Publications and Preprints

1. Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL
   Jiarui Yao*, Yifan Hao*, Hanning Zhang, Hanze Dong, Wei Xiong, Nan Jiang, Tong Zhang, NeurIPS 2025.
   

2. Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods
   Yifan Hao*, Xingyuan Pan*, Hanning Zhang*, Chenlu Ye, Rui Pan, Tong Zhang, ICML 2024.
   

3. Towards Better Generalization via Distributional Input Projection Network
   Yifan Hao*, Yanxin Lu*, Hanning Zhang, Xinwei Shen, Tong Zhang, Preprint.
   

4. Transformers as Multi-task Learners: Decoupling Features in Hidden Markov Models
   Yifan Hao*, Chenlu Ye*, Chi Han, Tong Zhang, Preprint.
   

5. Efficient Model Editing with Task Vector Bases: A Theoretical Framework and Scalable Approach
   Siqi Zeng, Yifei He, Weiqiu You, Yifan Hao, Yao-Hung Hubert Tsai, Makoto Yamada, Han Zhao, Preprint.
   

6. On the Benefits of Over-parameterization for Out-of-Distribution Generalization
   Yifan Hao*, Yong Lin*, Difan Zou, Tong Zhang, Preprint.
   

7. The Surprising Harmfulness of Benign Overfitting for Adversarial Robustness
   Yifan Hao, Tong Zhang, Preprint.
   

8. Spurious feature diversification improves out-of-distribution generalization
   Yong Lin*, Lu Tan*, Yifan Hao*, Honam Wong, Hanze Dong, Weizhong Zhang, Yujiu Yang, Tong Zhang, ICLR 2024.
   

9. Monte Carlo Sampling without Isoperimetry: A Reverse Diffusion Approach
   Xunpeng Huang*, Hanze Dong*, Yifan Hao, YI-An Ma, Tong Zhang, ICLR 2024.
   

10. SFQRA: Scaled Factor-augmented Quantile Regression with Aggregation in Conditional Mean Forecasting
    Lei Shu, Yifan Hao, Yu Chen, Qing Yang, Journal of Multivariate Analysis.
    

(* denotes equal contribution.)

Servie

Conference Reviewer: NeurIPS, ICML, ICLR, AISTATS, AAAI
Journal Reviewer: Journal of Machine Learning Research, SIAM Journal on Mathematics of Data Science

Contact me

If you are interested in discussing with me, feel free to contact me via email: yifanh12 AT Illinois DOT edu, yhaoah AT connect AT ust AT hk.