EDUCATION

BS in Data Science, Yuanpei College, Peking University

PUBLICATIONS

Looped Transformers for Length Generalization
Ying Fan, Yilun Du, Kannan Ramchandran, Kangwook Lee

Transformers Can Learn Meta-Skills for Task Generalization
Ying Fan, Steve Yadlowsky, Dimitris Papailiopoulos, Kangwook Lee

How to Solve Contextual Goal-Oriented Problems with Offline Datasets?
Ying Fan, Jingling Li, Adith Swaminathan, Aditya Modi, Ching-An Cheng

Domain Generalization with Nuclear Norm Regularization
Zhenmei Shi*, Yifei Ming*, Ying Fan*, Frederic Sala, Yingyu Liang. (* equal contribution)

DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models
Ying Fan*, Olivia Watkins, Yuqing Du, Hao Liu, Moonkyung Ryu, Craig Boutilier, Pieter Abbeel, Mohammad Ghavamzadeh, Kangwook Lee, Kimin Lee* (* equal contribution)

Algorithms for Optimal Adaptation of Diffusion Models to Reward Functions
Krishnamurthy Dj Dvijotham, Shayegan Omidshafiei, Kimin Lee, Katherine M. Collins, Deepak Ramachandran, Adrian Weller, Mohammad Ghavamzadeh, Milad Nasr, Ying Fan, Jeremiah Zhe Liu

Optimizing DDPM Sampling with Shortcut Fine-Tuning
Ying Fan, Kangwook Lee

Score-based Generative Modeling Secretly Minimizes the Wasserstein Distance
Dohyun Kwon, Ying Fan, Kangwook Lee

POEM: Out-of-distribution Detection with Posterior Sampling
Yifei Ming*, Ying Fan* and Yixuan Li (* equal contribution)

Model-based Reinforcement Learning for Continuous Control with Posterior Sampling
Ying Fan, Yifei Ming

EXPERIENCES

Visiting Student, UC Berkeley
Host: Kannan Ramchandran

Student Researcher, Google
Mentor: Kimin Lee

Research Intern, Microsoft Research
Mentor: Ching-An Cheng

HONORS AND AWARDS

Founder Scholarship, Peking University

Award for Academic Excellence, Peking University