Yunrui Zhang 张芸睿
ECE Ph.D. Student @ Cornell University
B.Eng., Tsinghua University (2024)
Hi! I am Yunrui Zhang (张芸睿), a first-year ECE Ph.D. student at Cornell University advised by Prof. Amy Kuceyeski and Prof. Mert Sabuncu. I obtained my bachelor's degree at Tsinghua University, where I was very fortunate to be advised by Prof. Gangtie Zheng, Prof. Mingguo Zhao and Prof. Rebing Wu.
My research interests lie broadly in the intersection of machine learning and advanced healthcare, including Magnetic Resonance Imaging (MRI)🧠, multi-modal medical imaging and surgical robotics🦾.
During my leisure time, I am an enthusiast of classic Chinese literature & poetry 📜, fiction 📖, piano 🎹 and musicals 🎶.
Photo taken in Jun 2024 with Jida.
",
which does not match the baseurl
("
") configured in _config.yml
.
baseurl
in _config.yml
to "
".
Cornell University
Ph.D. in Electrical and Computer Engineering Aug. 2024 - Present
Tsinghua University
B.Eng. in Automation Sep. 2020 - Jun. 2024
University of Illinois at Urbana-Champaign
Summer Research Intern Jul. 2023 - Sep. 2023
Yunrui Zhang, Emily S. Finn, Mert R. Sabuncu, Amy Kuceyeski
bioRxiv DOI:10.1101/2025.07.28.666907 Under review. 2025
How does the human brain respond while watching movies, and what can this reveal about individual traits? In this work, we show that certain movie clips can predict cognitive scores and sex from fMRI functional connectivity more effectively than five times as much resting-state data. For cognition prediction, a movie clip’s predictive power is strongly linked to how well it synchronizes brain activity across people and to the amount of social and human-related content. These effects were not observed for sex prediction.
Yunrui Zhang, Ruiyang Zhao, Zepeng Wang
International Society of Magnetic Resonance in Medicine (ISMRM) 2024 Power Pitch
In this work, we adapted and extended the self-supervised learning-based RAKI method by incorporating the FID dimension into a 3D, complex-valued convolutional network, for MRSI reconstruction. We improved the design by training a single network to handle multi-coil data simultaneously instead of the coil-by-coil interpolation in the original RAKI method. We demonstrate reduced aliasing by the proposed method and consequently improved spatiospectral processing results, using in vivo 1H-MRSI data.