BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Foundation Models in Robotics - Liyou Zhou (Cambridge)
DTSTART:20250122T110000Z
DTEND:20250122T123000Z
UID:TALK227182@talks.cam.ac.uk
CONTACT:Xianda Sun
DESCRIPTION:The advent of foundation models—large\, pre-trained models l
 ike GPT and CLIP—has revolutionised artificial intelligence\, enabling i
 mpressive generalisation and adaptability across diverse domains. In this 
 presentation\, we explore how these models are beginning to reshape roboti
 cs by serving as versatile building blocks for perception\, reasoning\, an
 d action. The talk will cover seminal papers in Vision-Language-Action mod
 els and World modelling. The talk will require audience have a general wor
 king understanding of foundation models.
LOCATION:Cambridge University Engineering Department\, CBL Seminar room BE
 4-38.
END:VEVENT
END:VCALENDAR