Xin Liu

Xin Liu is a Research Scientist at Google Consumer Health Research and a research affliate in the Paul G. Allen School of Computer Science & Engineering at the University of Washington. He received his PhD in Computer Science from the University of Washington in 2023, where he was advised by Shwetak Patel and Daniel McDuff. His PhD research was supported by the Google PhD Fellowship .

Before joining UW, he obtained his bachelor’s degree in computer science from the University of Massachusetts Amherst in 2018, where he started his mobile health research journey with Sunghoon Ivan Lee .

His work is at the intersection of ubiquitous and mobile computing, machine learning, and health. In Xin's research, he studies how to enable mobile health + AI at scale, with a focus on building foundation models for sensor and consumer health data.

Email  /  CV  /  Bio  /  Google Scholar  /  Twitter  /  Github  /  Linkedin

profile photo
Work Experience
google_logo Consumer Health Research Full-time Research Scientist (April, 2023 - Present)
google_logo Consumer Health Research Research Intern + Part-time Student Researcher (Sep, 2021 - April, 2023)
microsoft_logo Human Understanding and Empathy Group Research Intern (June, 2021 - Sep, 2021)
octoml_logo Machine Learning Systems Team Part-time Intern (Nov, 2020 - May, 2021)
ai2_logo Allen Institute for AI Intern (June, 2019 - Sep, 2019)
Selected Publication

See a full-list of publication at my Google Scholar. I publish papers under UW / Google.

Motion Matters: Neural Motion Transfer for Better Camera Physiological Measurement
Akshay Paruchuri, Xin Liu, Yulu Pan, Shwetak Patel, Daniel McDuff, Soumyadip Sengupta
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2024)
Oral, Top 53 out of 2042 Submissions (Top 2.6%)

pdf / bibtex
rPPG-Toolbox: Deep Remote PPG Toolbox
Xin Liu, Girish Narayanswamy*, Akshay Paruchuri*, Xiaoyu Zhang, Jiankai Tang, Yuzhe Zhang, Roni Sengupta, Shwetak Patel, Yuntao Wang, Daniel McDuff
Conference on Neural Information Processing Systems (NeurIPS' 23 Datasets and Benchmarks Track) * denotes equal contribution

pdf / bibtex
Large Language Models are Few-Shot Health Learners
Xin Liu, Daniel McDuff, Geza Kovacs, Isaac Galatzer-Levy, Jacob Sunshine, Jiening Zhan, Ming-Zher Poh, Shun Liao, Paolo Di Achille, Shwetak Patel
Arxiv, 2023

pdf / bibtex
SimPer: Simple Self-Supervised Learning of Periodic Targets
Yuzhe Yang, Xin Liu, Jiang Wu, Silviu Borac, Dina Katabi, Ming-Zher Poh, Daniel McDuff
International Conference on Learning Representations (ICLR' 23)
Oral, Notable Top 5%, Review Ranked Top 5 among 4922 Submissions (Top 0.1%)

pdf / bibtex
GLOBEM: Cross-Dataset Generalization of Longitudinal Human Behavior Modeling
Xuhai Xu, Xin Liu, Han Zhang, Weichen Wang, Subigya Kumar Nepal, Kevin S. Kuehn, Jeremy F Huckins, Margaret E Morris, Paula S. Nurius, Eve Ann Riskin, Shwetak Patel, Tim Althoff, Andrew Campbell, Anind Dey, Jennifer Mankoff
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT/Ubicomp 2023)
Distinguished Paper Award

pdf / bibtex
SCAMPS: Synthetics for Camera Measurement of Physiological Signals
Daniel McDuff, Miah Wander, Xin Liu, Brian Hill, Javier Hernandez, Jonathan Lester, Tadas Baltrusaitis
Conference on Neural Information Processing Systems (NeurIPS' 22) Oral, Top 1%

pdf / bibtex
Efficientphys: Enabling simple, fast and accurate camera-based vitals measurement
Xin Liu, Brian Hill, Ziheng Jiang, Shwetak Patel, Daniel McDuff
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023)
pdf / bibtex
Using High-Fidelity Avatars to Advance Camera-based Cardiac Pulse Measurement
Daniel McDuff, Javier Hernandez, Xin Liu, Josh Fromm, Erroll Wood, Tadas Baltrušaitis
IEEE Transactions on Biomedical Engineering (TBME 2022)
pdf / bibtex
MobilePhys: Personalized Mobile Camera-Based Contactless Physiological Sensing
Xin Liu, Yuntao Wang, Sinan Xie, Xiaoyu Zhang, Zixian Ma, Daniel McDuff, Shwetak Patel
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT/Ubicomp 2022)
pdf / bibtex
MetaPhys: Few-Shot Adaptation for Non-Contact Physiological Measurement
Xin Liu, Ziheng Jiang, Josh Fromm, Xuhai Xu, Shwetak Patel, Daniel McDuff
ACM Conference on Health, Inference, and Learning (ACM-CHIL 2021)
Selected Media: IEEE Spectrum , ACM TechNews , GeekWire , UW News
pdf / bibtex
Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement
Xin Liu, Josh Fromm, Shwetak Patel, Daniel McDuff
Conference on Neural Information Processing Systems (NeurIPS' 20)
Oral, Top 1%, 105 out of 9454 Submissions
Selected Media: Microsoft Research Webinar, Microsoft Research Blog, ZDNet
pdf / bibtex
SplitSR: An End-to-End Approach to Super-Resolution on Mobile Devices
Xin Liu, Yuang Li, Josh Fromm, Yuntao Wang, Ziheng Jiang, Alex Mariakakis, Shwetak Patel
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT/Ubicomp 2021)
pdf / bibtex
The Use of A Finger-Worn Accelerometer for Monitoring of Hand Use in Ambulatory Settings
Xin Liu, Smita Rajan, Nathan Ramasarma, Paolo Bonato and Sunghoon Ivan Lee
IEEE Journal of Biomedical and Health Informatics (J-BHI 2019)
Cover Article Nominee
pdf / bibtex
Teaching Experience

Winter 2021/2022 - TECHIN 513: Managing Data and Signal Processing, Graduate Teaching Assistant

Fall 2017 - CS328: Mobile Health & Sensing, Undergraduate Course Assistant
Outstanding Course Assistant Award


During my undergraduate studies, I spent a huge amount of effort to push the international community to engage various leadership experiences at the university. I was the first international peer mentor in the residential life office and the first international student consultant in the department of information and technology. I worked at six different departments during my undergrd years :p

During my free time, I enjoy snowboarding, climbing and playing tennis with my partner. I am also a big fan of NBA.

Website Credits to Jon Barron source code and Siddhartha Gairola source code