BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Why don't models generalize? - Prof. Yonatan Bisk (CMU)
DTSTART:20251204T140000Z
DTEND:20251204T150000Z
UID:TALK238921@talks.cam.ac.uk
CONTACT:Shun Shao
DESCRIPTION:Abstract: Why don't models generalize? Can we characterize thi
 s issue in current architectures like transformers or diffusion models? Do
  we have ideas on a path forward? In this talk\, I'll plan to discuss a fe
 w papers we have in this line of work and also fail to truly answer your q
 uestions. \n\nBio: Yonatan Bisk is an assistant professor of computer scie
 nce at Carnegie Mellon University – Language Technologies Institute and 
 Robotics Institute (courtesy). He received his PhD from the University of 
 Illinois at Urbana-Champaign working on unsupervised Bayesian models of li
 nguistic syntax.\n\nHe runs the CLAW lab\, Connecting Language to Action a
 nd the World. His group works on grounded and embodied language and commun
 ication\, placing perception and interaction as central to how language is
  learned and understood. He has held appointments at USC's ISI (working on
  grounding)\, the University of Washington (for commonsense research)\, Mi
 crosoft Research (for vision+language)\, and Meta Inc (for Embodied AI).
LOCATION:https://cam-ac-uk.zoom.us/j/97599459216?pwd=QTRsOWZCOXRTREVnbTJBd
 XVpOXFvdz09
END:VEVENT
END:VCALENDAR