Yuzhe Yang

Hi there! I am a fifth-year Ph.D. student at Computer Science & Artificial Intelligence Laboratory (CSAIL) at MIT, working with Prof. Dina Katabi. Before coming to MIT, I received my B.S. with honors from Peking University.

My research interests lie in the intersection of machine learning and digital health. I work on fundamental learning algorithms for model robustness and generalization against data biases and distribution shifts (ICML'19, CVPR'20, NeurIPS'20, ICML'21, ECCV'22), and building AI-based frameworks for transforming real-world health applications with novel modalities and solutions (Nature Medicine'22, Science Translational Medicine'22, UbiComp'20).

/ / / / yuzhe [at] mit [dot] edu

News

Looking for students to do research with me on generalizable ML / AI for health. Feel free to shoot me an email if you are interested.

[08/2022] Single first-author paper on AI-based biomarker for Parkinson's disease is published at Nature Medicine.
[08/2022] Gave a talk at Google Health Research.
[08/2022] Paper on contactless in-home monitoring of gait in Parkinson's disease is accepted to Science Translational Medicine.
[06/2022] I received the 2022 MathWorks Ph.D. Fellowship.

[03/2022] I have been selected as a Highlighted Reviewer (Top 8%) for ICLR 2022.

[05/2021] Paper on imbalanced regression is accepted to ICML 2021 as a Long Talk (3%).

[04/2020] My research on contactless human sleep sensing with AI has been used to let doctors monitor COVID-19 patients from a distance.
[12/2019] Paper on structured reinforcement learning is accepted to ICLR 2020 as an Oral Presentation (1.8%).

[Show more]

Publications (show selected / show by date / show by topic)
Research Topics: AI-Enabled Digital Health / Robust & Generalizable ML / Data & Label Efficient ML

Talks (Selected)

2022 @ Google Health Research
2022 @ Citadel Securities, PhD Summit: Delving into Deep Imbalanced Regression
2021 @ Tsinghua, AI TIME: Delving into Deep Imbalanced Regression
2021 @ NTU, MMLab: Rethinking Learning from Imbalanced Data
2021 @ TechBeat: Imbalanced Learning: From Semi-supervision, Self-supervision, to Deep Imbalanced Regression
2020 @ Johns Hopkins University, Artificial Intelligence Society: Algorithms & Applications for AI-driven Healthcare
2020 @ UC Berkeley, JiaoLab Group: Rethinking the Value of Labels for Improving Class-Imbalanced Learning

Honors and Awards (Selected)

MathWorks Ph.D. Fellowship, 2022-2023
Highlighted Reviewer (Top 8%), ICLR 2022
MathWorks Ph.D. Fellowship, 2021-2022
Best Undergraduate Dissertation Award, EECS Dept., Peking Univ., 2018
First Prize (No.1 out of 23 finalists), IEEE ComSoc Student Competition: Communication Technology Changing the World, 2017
National Scholarship (highest honor), The Chinese Government, 2017
HuaWei Scholarship, 2017
Samsung Scholarship, 2016

Professional Service

Conference Reviewer: NeurIPS, ICML, ICLR (Highlighted Reviewer), CVPR, ICCV, ECCV, IJCAI, AAAI, UAI
Program Committee Member: AAAI, IJCAI, UAI
Journal Reviewer: TPAMI, TMLR, IEEE TKDE, IEEE TIFS, IEEE TVT, IEEE IoT-J

Press

AI-based Biomarker for Parkinson's Disease was covered by: MIT News, CSAIL News, Forbes, NVIDIA Technical Blog, The Washington Post, Stat News, Boston Globe, FierceBiotech, New Atlas, University of Rochester, Yahoo, Parkinson's News Today, Futurity, BioSpace, Times of India, AzoRobotics, and other media outlets.
Contactless In-Home Respiratory and Behavior Monitoring of COVID-19 was covered by: Wall Street Journal, CSAIL News, Yahoo News, UK Time News, The Next Web, Tech Crunch, Engadget, VentureBeat, Electronics 360, Tech Times, Grid Daily, AI in Healthcare, DNYUZ, Tech Register, Inc., and other media outlets.
BodyCompass was covered by: MIT News, Engadget, Yahoo, Technology Networks, Sleep Review, TechTimes, SlashGear, TechSpot, Hackster, New Atlas, BGR, and other media outlets.

Contact

MIT Computer Science & Artificial Intelligence Lab
32-G928, 32 Vassar St., Cambridge, MA 02139
yuzhe [at] mit (dot) edu