BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Towards Scalable Foundation Models for Wearable Sensing - Shyam Ta
 ilor\, Google
DTSTART:20250211T160000Z
DTEND:20250211T170000Z
UID:TALK219766@talks.cam.ac.uk
CONTACT:Cecilia Mascolo
DESCRIPTION:Abstract: Consumer wearable devices have seen remarkable progr
 ess in recent years\, becoming more accurate\, pervasive\, and affordable.
   Despite these advancements\, large-scale foundation models trained on w
 earable data are a relatively new phenomenon\, unlike in many other domain
 s.  This talk will explore the technical landscape currently limiting pro
 gress in this area\, and present our new work\, "Scaling Wearable Foundati
 on Models\," recently accepted to ICLR.\n\nBio: Shyam Tailor is a senior r
 esearch scientist at Google\, specializing in the development of practical
 \, scalable techniques for harnessing large foundational models in health.
  With a strong track record of both research and real-world impact\, Shyam
  has contributed to several flagship features on Google Fitbit devices\, i
 ncluding the first widely available GenAI-powered feature\, as well as adv
 anced sensing algorithms for heart rate and activity monitoring which have
  been widely applauded by the press. Shyam completed his PhD at the Univer
 sity of Cambridge in under three years\, where his research\, under the gu
 idance of Professor Nic Lane\, focused on creating resource-efficient mach
 ine learning algorithms. His work has earned recognition across major conf
 erences and workshops\, with publications at prestigious venues including 
 ICLR\, ICML\, MLSys\, ECCV\, and Ubicomp/IMWUT\, and he has won multiple b
 est paper awards for his contributions.\n\n
LOCATION:Online
END:VEVENT
END:VCALENDAR