I am a second-year Ph.D. student in Computer Science at University of Illinois at Urbana-Champaign. I earned my dual master degree from Tsinghua University and Columbia University, and my bachelor from Fudan University.

I’m always interested in exploring new and exciting machine learning topics. I value research that is, at the very least, empirically useful; ideally, grounded in theory; and, at best, elegant.

I’ve previously worked on Data-centric ML and Trustworthy ML, with a particular focus on Large Language Models. My most recent research interests include:

• RL Fine-tuning for LLMs
• LLM Reasoning
• LLM Evaluation

🚀 I am currently actively seeking a Research Scientist Internship for Summer 2026. If you think there might be a good fit, feel free to reach out!

📝 Preprints and Publications

Preprints and Workshop Papers:

• Learning a Zeroth-Order Optimizer for Fine-Tuning LLMs, Kairun Zhang$^{\dagger}$, Haoyu Li$^{\dagger}$, Yanjun Zhao$^{\dagger}$, Yifan Sun, Huan Zhang
• SVIP: Towards Verifiable Inference of Open-source Large Language Models, Yifan Sun$^{\dagger}$, Yuhang Li$^{\dagger}$, Yue Zhang, Yuchen Jin, Huan Zhang, Socially Responsible and Trustworthy Foundation Models Workshop at NeurIPS 2025
• When Reasoning Meets Its Laws, Junyu Zhang$^{\dagger}$, Yifan Sun$^{\dagger}$, Tianang Leng$^{\dagger}$, Jingyan Shen$^{\dagger}$, Ziyin Liu, Paul Pu Liang, Huan Zhang, Efficient Reasoning Workshop at NeurIPS 2025 (Oral Presentation)

Selected Publications:

• Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay, Yifan Sun$^{\dagger}$, Jingyan Shen$^{\dagger}$, Yibin Wang$^{\dagger}$, Tianyu Chen, Zhendong Wang, Mingyuan Zhou, Huan Zhang, NeurIPS 2025
• MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning, Jingyan Shen$^{\dagger}$, Jiarui Yao$^{\dagger}$, Rui Yang$^{\dagger}$, Yifan Sun, Feng Luo, Rui Pan, Tong Zhang, Han Zhao, EMNLP 2025 (Main Conference) — Outstanding Paper Award (7 selected out of 8,174 submissions)
• AutoScale: Scale-Aware Data Mixing for Pre-Training LLMs, Feiyang Kang$^{\dagger}$, Yifan Sun$^{\dagger}$, Bingbing Wen, Si Chen, Dawn Song, Rafid Mahmood, Ruoxi Jia, COLM 2025
• The Emperor’s New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination, Yifan Sun$^{\dagger}$, Han Wang$^{\dagger}$, Dongbai Li$^{\dagger}$, Gang Wang, Huan Zhang, ICML 2025
• 2D-OOB: Attributing Data Contribution through Joint Valuation Framework, Yifan Sun$^{\dagger}$, Jingyan Shen$^{\dagger}$, Yongchan Kwon, NeurIPS 2024
• Get More for Less: Principled Data Selection for Warming Up Fine-Tuning in LLMs, Feiyang Kang, Hoang Anh Just$^{\dagger}$, Yifan Sun$^{\dagger}$, Himanshu Jahagirdar$^{\dagger}$, Yuanzhi Zhang, Rongxing Du, Anit Kumar Sahu, Ruoxi Jia, ICLR 2024
• Data Acquisition: A New Frontier in Data-centric AI, Lingjiao Chen, Bilge Acun, Newsha Ardalani, Yifan Sun, Feiyang Kang, Hanrui Lyu, Yongchan Kwon, Ruoxi Jia, Carole-Jean Wu, Matei Zaharia, James Zou, Transactions on Machine Learning Research (TMLR)

$^{\dagger}$ indicates these authors contributed equally to this work. See my Google Scholar for earlier publications.

🥇 Honors and Awards

• Outstanding Graduate of Beijing, Beijing Municipal Education Commission, 2024
• Benjamin Miller Memorial Fellowship, Columbia University, 2023
• National Scholarship for Graduates, Ministry of Education of China, 2022
• Outstanding Graduate of Shanghai, Shanghai Municipal Education Commission, 2021
• Excellent Undergraduate Thesis Award, Fudan University, 2021
• National Scholarship for Undergraduates, Ministry of Education of China, 2018, 2019, 2020

🧑‍⚖️ Academic Service

• Reviewer: NeurIPS, ICML, ICLR, EMNLP

🏢 Industry Experience

• Applied Scientist Intern, AGI Foundations, Amazon, May 2025 – Aug 2025
  • Conducted research on LLM post-training