Zechen Li | PhD Candidate at UNSW

About Me

I am a third-year PhD candidate in Computer Science at the University of New South Wales (UNSW), Sydney, supervised by Prof. Flora Salim and Prof. Hao Xue. I am also a Student Researcher at Google Health, working on the intersection of multimodal foundation models and health AI.

My research lies at the intersection of wearable sensing, large language models, and intelligent health systems. I am broadly interested in human activity recognition, continuous glucose monitoring, multimodal health modeling, and LLM4Health, with a focus on interpretable reasoning, personalized insights, and intelligent agents for real-world healthcare applications.

News

RubricsTree is out, building an expert-aligned evaluation tree for scalable personal health agents. (Jun 16, 2026)
AgentMob is out, bringing adaptive evidence-gathering to training-free mobility prediction. (Jun 3, 2026)
Excited to share GlucoFM, my Google Health work on dual-stream foundation models for reusable CGM representations. (May 29, 2026)
AnyMo is out, bringing setup-agnostic human motion modeling closer to real-world sensing. (May 21, 2026)
Happy to share CGM-JEPA, my first Google work on predictive self-supervised learning for CGM signals. (May 19, 2026)
MAGE is out, helping LLM agents improve with the knowledge graphs they co-evolve. (May 11, 2026)
Thrilled that ZARA has been accepted to ACL 2026 as an oral presentation! See you in San Diego! (Apr 9, 2026)
COMODO accepted to IMWUT / UbiComp 2026. See you in Shanghai! (Apr 1, 2026)
Started as a Student Researcher at Google Health in Mountain View. (Feb 2, 2026)
SensorLLM accepted to EMNLP 2025. See you in Suzhou! (Aug 20, 2025)

Education

University of New South Wales, Sydney

PhD in Computer Science

Advisors: Prof. Flora Salim and Prof. Hao Xue

Sep 2023 - Present

Northeastern University, Boston

Master of Science in Data Analytics Engineering

GPA: 3.917/4.0

2019 - 2021

Southern Medical University, Guangzhou

Bachelor of Engineering in Biomedical Engineering (Information Technology)

2015 - 2019

Experience

Google

Student Researcher

Mentors: Dr. Ahmed Abdelhadi Metwally, Prof. Yuzhe Yang

Feb 2026 - Present

UNSW Sydney

Casual Academic (Tutor)

COMP6713 NLP COMP9517 Computer Vision DATA9001 Data Science Fundamentals COMP9444 Neural Networks & Deep Learning

Feb 2025 - Present

Singapore University of Technology and Design

Visiting Researcher

Advisor: Prof. Wei Lu

Mar 2023 - Jul 2023

University of Copenhagen

Research Assistant (Part-time)

Advisor: Prof. Anders Søgaard

Aug 2021 - Aug 2022

UC San Diego

Research Assistant (Part-time)

Advisor: Prof. Pengtao Xie

Jun 2020 - Mar 2021

Selected Publications

*: equal contribution

GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring.

Zechen Li, Keerthana Natarajan, Weizhi Zhang, Menglian Zhou, Simon A. Lee, Yuwei Zhang, Maxwell A. Xu, Zeinab Esmaeilpour, Flora D. Salim, Mark Malhotra, Lindsey Sunden, Shwetak Patel, Yuzhe Yang, Ahmed A. Metwally.

arXiv, 2026.

Paper
CGM-JEPA: Learning Consistent Continuous Glucose Monitor Representations via Predictive Self-Supervised Pretraining.

Hada Melino Muhammad*, Zechen Li*, Flora Salim, Ahmed A. Metwally.

arXiv, 2026.

Paper Code
ZARA: Training-Free Motion Time-Series Reasoning via Evidence-Grounded LLM Agents.

Zechen Li, Baiyu Chen, Hao Xue, Flora D. Salim.

ACL Main (oral), 2026.

Paper Code Poster Video
SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognition.

Zechen Li, Shohreh Deldari, Linyao Chen, Hao Xue, Flora D. Salim.

EMNLP Main, 2025.

Paper Code Poster Video
QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual Reasoning.

Zechen Li, Anders Søgaard.

NAACL Findings, 2022.

Paper Code
Self-supervised Regularization for Text Classification.

Meng Zhou*, Zechen Li*, Pengtao Xie.

TACL, 2021. Oral Presentation at NAACL 2021

Paper Code Video
RubricsTree: Scalable and Evolving Open-Ended Evaluation of Personal Health Agents across Health Memory and Medical Skills.

Weizhi Zhang, Zechen Li, Hamid Palangi, Ben Graef, A. Ali Heydari, Simon A. Lee, Salman Rahman, Ray Luo, Zeinab Esmaeilpour, Erik Schenck, Chloe Zhang, Yamin Li, Menglian Zhou, Philip S. Yu, Daniel McDuff, Lindsey Sunden, Mark Malhotra, Shwetak Patel, Ahmed A. Metwally.

arXiv, 2026.

Paper
Towards Efficient and Evidence-Grounded Mobility Prediction with LLM-Driven Agent.

Linyao Chen, Qinlao Zhao, Zechen Li, Mingming Li, Likun Ni, Jinyu Chen, Yuhao Yao, Xuan Song, Noboru Koshizuka, Hiroki Kobayashi.

arXiv, 2026.

Paper Code
AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild.

Baiyu Chen, Zechen Li, Wilson Wongso, Lihuan Li, Xiachong Lin, Hao Xue, Benjamin Tag, Flora Salim.

arXiv, 2026.

Paper Project Code
MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs.

Ruiyi Yang, Zechen Li, Hao Xue, Imran Razzak, Flora D. Salim.

arXiv, 2026.

Paper
COMODO: Cross-modal Video-to-IMU Distillation for Efficient Egocentric Human Activity Recognition.

Baiyu Chen, Wilson Wongso, Zechen Li, Yonchanok Khaokaew, Hao Xue, Flora Salim.

IMWUT/UbiComp, 2026.

Paper Code
On the Generation of Medical Dialogs for COVID-19.

Meng Zhou, Zechen Li, Bowen Tan, Guangtao Zeng, Wenmian Yang, Xuehai He, Zeqian Ju, Subrato Chakravorty, Shu Chen, Xingyi Yang, Yichen Zhang, Qingyang Wu, Zhou Yu, Kun Xu, Eric Xing, Pengtao Xie.

ACL Short Paper, 2021.

Paper