Selected Preprints and Publications

Your Benchmark Is an Empirical Measure Over Difficulty

Yifan Sun^†, Naicheng Yu^†, Jiawen Gong^†, Jingyan Shen, Huan Zhang

NeurIPS · 2026

Understanding Reasoning from Pretraining to Post-Training

Jingyan Shen^†, Ang Li^†, Salman Rahman, Yifan Sun, Micah Goldblum, Matus Telgarsky, Pavel Izmailov

NeurIPS · 2026

When Reasoning Meets Its Laws

Junyu Zhang^†, Yifan Sun^†, Tianang Leng^†, Jingyan Shen^†, Ziyin Liu, Paul Pu Liang, Huan Zhang

NeurIPS · 2026

MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models

Han Wang^†, Yifan Sun^†, Brian Ko^†, Mann Talati, Jiawen Gong, Zimeng Li, Naicheng Yu, Xucheng Yu, Wei Shen, Vedant Jolly, Huan Zhang

COLM · 2026

Learning a Zeroth-Order Optimizer for Fine-Tuning LLMs

Kairun Zhang^†, Haoyu Li^†, Yanjun Zhao^†, Yifan Sun, Huan Zhang

ICML · 2026

Influence-Preserving Proxies for Gradient-Based Data Selection in LLM Fine-Tuning

Sirui Chen^†, Yunzhe Qi^†, Mengting Ai, Yifan Sun, Ruizhong Qiu, Jiaru Zou, Jingrui He

ICLR · 2026

Improving Data Efficiency for LLM Reinforcement Fine-Tuning Through Difficulty-targeted Online Data Selection and Rollout Replay

Yifan Sun^†, Jingyan Shen^†, Yibin Wang^†, Tianyu Chen, Zhendong Wang, Mingyuan Zhou, Huan Zhang

NeurIPS · 2025

MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning

Jingyan Shen^†, Jiarui Yao^†, Rui Yang^†, Yifan Sun, Feng Luo, Rui Pan, Tong Zhang, Han Zhao

EMNLP (Main Conference) · 2025

Outstanding Paper Award (7 selected out of 8,174 submissions)

AutoScale: Scale-Aware Data Mixing for Pre-Training LLMs

Feiyang Kang^†, Yifan Sun^†, 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^†, Han Wang^†, Dongbai Li^†, Gang Wang, Huan Zhang

ICML · 2025

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

Journal of Data-centric Machine Learning Research · 2025

2D-OOB: Attributing Data Contribution through Joint Valuation Framework

Yifan Sun^†, Jingyan Shen^†, Yongchan Kwon

NeurIPS · 2024

Get More for Less: Principled Data Selection for Warming Up Fine-Tuning in LLMs

Feiyang Kang, Hoang Anh Just^†, Yifan Sun^†, Himanshu Jahagirdar^†, Yuanzhi Zhang, Rongxing Du, Anit Kumar Sahu, Ruoxi Jia

ICLR · 2024

SVIP: Towards Verifiable Inference of Open-source Large Language Models

Yifan Sun^†, Yuhang Li^†, Yue Zhang, Yuchen Jin, Huan Zhang

Socially Responsible and Trustworthy Foundation Models Workshop at NeurIPS 2025 (Oral Presentation) · 2025

Direct Preference Optimization with Rating Information: Practical Algorithms and Provable Gains

Luca Viano, Ruida Zhou, Yifan Sun, Mahdi Namazifar, Volkan Cevher, Shoham Sabach, Mohammad Ghavamzadeh

Preprint · 2026