Ying Fan

ABOUT

I am a Ph.D. candidate in Department of Computer Sciences at UW-Madison, advised by Prof. Kangwook Lee. Before that, I obtained Bachelor's degree in Data Science from Yuanpei College, Peking University. My research interest lies in machine learning, with a recent focus on sequential learning problems including reinforcement learning, diffusion models and LLMs.
I am actively seeking industry research positions and postdoc positions starting in 2025.


[CV]  [Google Scholar]

EDUCATION

PhD in Computer Science, UW-Madison

IN PROGRESS

BS in Data Science, Yuanpei College, Peking University

SEP 2015 - JUL 2019


PUBLICATIONS

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

 

 

MATH-AI
NeurIPS 2024 Workshop
pdf

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

 

Compositional Learning
NeurIPS 2024 Workshop
pdf

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

 

NeurIPS 2024
pdf code

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

 

CPAL 2024
Oral
pdf code

 

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)

 

NeurIPS 2023
pdf talk code

 

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

 

Frontiers4LCD
ICML 2023 Workshop
pdf

 

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

 

ICML 2023
pdf talk code

 

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

 

NeurIPS 2022
pdf talk code

 

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

 

ICML 2022
Oral (2%)
pdf talk code

 

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

 

ICML 2021
Oral (3%)
pdf talk code

 


EXPERIENCES

Research Intern, Google
Mentor: Qifei Wang

 

May 2024 - Aug 2024

Visiting Student, UC Berkeley
Host: Kannan Ramchandran

 

Mar 2024 - May 2024

Student Researcher, Google
Mentor: Kimin Lee

 

Feb 2023 - Nov 2023

Research Intern, Microsoft Research
Mentor: Ching-An Cheng

 

Jun 2022 - Aug 2022


HONORS AND AWARDS

Rising Stars in Maching Learning, 2024

 

NeurIPS Scholar Award, 2023

 

Founder Scholarship, Peking University

 

Award for Academic Excellence, Peking University

 


CONTACT

Email
yingfan [at] cs [dot] wisc [dot] edu

Social Links