Yunzhen Feng
Machine Learning Researcher
I work on pretraining scaling science.
I received my Ph.D. in Data Science from New York University, where I was advised by Prof. Julia Kempe. During my Ph.D., I also collaborated with Prof. He He, Prof. Tim G. J. Rudner, Prof. Qi Lei, and Prof. Yaqi Duan.
My Ph.D. research explored how data and compute shape the capabilities of language models. Specifically, I focused on scaling laws for learning from real and synthetic data, and on reinforcement learning for post-training and reasoning.
I previously interned at Meta Superintelligence Labs (MSL) and Fundamental AI Research (FAIR).
I graduated from Peking University with a bachelor's in Applied Mathematics (Honor Track). Back then, I was advised by Prof. Bin Dong , Prof. Di He, and was fortunate to work with Prof. Yue M. Lu from Harvard.
Feel free to contact me for research collaborations or other engagements.
Selected Publications
What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT
Yunzhen Feng, Julia Kempe, Cheng Zhang, Parag Jain, Anthony Hartshorn.
International Conference on Machine Learning (ICML), 2026.
NeurIPS Workshop on Efficient Reasoning, 2025, Spotlight.
[Paper]
PILAF: Optimal Human Preference Sampling for Reward Modeling.
Yunzhen Feng, Ariel Kwiatkowski, Kunhao Zheng, Julia Kempe, Yaqi Duan.
International Conference on Machine Learning (ICML), 2025.
[Paper]
Strong Model Collapse.
Elvis Dohmatob, Yunzhen Feng, Arjun Subramonian, Julia Kempe.
International Conference on Learning Representations (ICLR), 2025, Spotlight.
[Paper]
Covered Media: [新智元] [机器之心] [German Radio Deutschlandfunk Series]
Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification.
Yunzhen Feng*, Elvis Dohmatob*, Pu Yang*, François Charton, Julia Kempe.
International Conference on Learning Representations (ICLR), 2025.
[Paper]
Covered Media: [Nature News] [Communications of the ACM] [Transformer Ai.] [The NYU Data Science News] [ MarkTechPost]
A Tale of Tails: Model Collapse as a Change of Scaling Laws
Yunzhen Feng*, Elvis Dohmatob*, Pu Yang, François Charton, Julia Kempe.
International Conference on Machine Learning (ICML), 2024.
[Paper]
Covered Media: [New York Times] [Les Echos] [The Register] [The Globe and Mail]
Do Efficient Transformers Really Save Computation?
Kai Yang, Jan Ackermann, Zhenyu He, Guhao Feng, Bohang Zhang, Yunzhen Feng, Qiwei Ye, Di He, Liwei Wang.
International Conference on Machine Learning (ICML), 2024.
[Paper]
Education
New York University, New York, NY. Ph.D. in Data Science. 2021 – 2026.
Peking University, Beijing, China. Bachelor of Science in Applied Mathematics (Honor Track). 2017 – 2021.
Miscellaneous
I am an outdoor lover. I climbed the Luodui Mount (6010m Snowberg) at Tibet, China in August, 2021. I have also served as the teaching assistant of *Outdoor Exploration* at Peking University. Outdoor experiences really help shape my personality and life methodology.