BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Foundation Models and Agentic AI for Human Physiology - Yuzhe Yang
 \, UCLA and Google
DTSTART:20260414T150000Z
DTEND:20260414T160000Z
UID:TALK244543@talks.cam.ac.uk
CONTACT:Cecilia Mascolo
DESCRIPTION:Human physiology is becoming a new frontier for general-purpos
 e AI. Unlike text and images\, physiological signals are continuous\, mult
 imodal\, and tightly coupled with both short-term dynamics and long-term h
 ealth outcomes. In this talk\, I will present our recent work on sleep fou
 ndation models and language-grounded understanding of sleep physiology. I 
 will then discuss wearable foundation models and benchmarks with the goal 
 of learning generalizable representations from large-scale real-world sens
 ing data for personal health. Finally\, I will cover health reasoning and 
 agentic AI for physiological time series\, and a broader vision for AI sys
 tems that can interpret\, reason over\, communicate about\, and support ac
 tion on human physiology.\n\nbio: Yuzhe Yang is an Assistant Professor of 
 Computational Medicine and Computer Science at UCLA\, where he directs the
  Health Intelligence Lab. He is also a visiting faculty researcher at Goog
 le. He received his Ph.D. in Computer Science at MIT. His research interes
 ts include machine learning\, artificial intelligence\, and their applicat
 ions in science\, medicine\, and human health. His research has been publi
 shed in Nature\, Nature Medicine\, NeurIPS\, ICML\, and ICLR\, featured in
  media outlets such as WSJ\, Forbes\, and BBC\, and recognized by the AMIA
  Doctoral Dissertation Award and Forbes 30 Under 30.
LOCATION:Computer Lab\, FW26 and Online
END:VEVENT
END:VCALENDAR