Hi, my name is Chen Liu (刘晨).
Email: chen DOT liu DOT cl2482 AT yale DOT edu.
Open to research internship (Summer 2025). Please let me know if you have opportunities in spatial-temporal modeling, vision models, AI in healthcare, or related fields.
I am currently a 3rd-year PhD candidate at Yale University. My research explores both theory and application of machine learning. On the theory side, I focus on helping neural networks learn better representations in the latent space, and one of my most recent work focus on modeling spatial-temporal dynamics in irregularly-sampled image series. On the application side, I extend my research to medical imaging and other biomedical data.
Prior to pursuing my PhD, I graduated from Columbia University in 2019 with a master degree in Electrical Engineering. In my first industry job, I worked at a startup company named Matic on computer vision and SLAM. Then I worked as a senior research scientist at GE Healthcare, on deep learning in medical imaging applications.
PhD, Computer Science, 2022 ~ 2027
Yale University
MS, Electrical Engineering, 2018 ~ 2019
Columbia University
BS, Electrical Engineering, 2014 ~ 2018
Bucknell University
Middle & High School, 2007 ~ 2014
Shanghai Foreign Language School
2024.07 🎉 I wrote a tool to generate your Google Scholar Citation World Map.
2024.06 🎉 My first PhD project, CUTS has been accepted to MICCAI 2024.
2024.01 🎉 Our paper on entropy and MI for deep neural networks has been accepted to an ICML 2023 Workshop and an IEEE Information Theory conference (CISS).
2022.08 🎉 Started my PhD program at Krishnaswamy Lab, Yale University.
2022.06 🎉 Recognized as an Outstanding Reviewer at ICML 2022.
Journal Reviewer
Conference Program Committee Member
Teaching Fellow
(Spatial-Temporal Modeling) We predict disease progression trajactories in the image space with position-parameterized neural differential equations in multiscale joint patient representations.
We propose a framework to measure the entropy and mutual information in high dimensions and is applicable to neural network representations.