BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium: Learning to reason over vision and language
DTSTART:20211213T161500
DTEND:20211213T171500
DTSTAMP:20260414T072359Z
UID:089fcc64627fe28a7bb2dcf6d952eba4fdd2d1a10f90b8419003fda9
CATEGORIES:Conferences - Seminars
DESCRIPTION:By: Damien Teney - Idiap Research Institute\nVideo of his talk
 \n\nAbstract\nIn this talk\, he will present some activities of his group 
 at the intersection of computer vision and natural language processing. We
  will see how tasks such as image captioning and visual question answering
  can serve as testbeds for complex reasoning\, out-of-distribution general
 ization\, and robustness to distribution shifts. He will present various a
 pproaches explored in his group that aim to expand the limits of statistic
 al machine learning\, such as causal reasoning and meta learning. The aim 
 of his work is to go beyond the classical i.i.d. setting\, learn models th
 at generalize out-of-distribution\, and increase their robustness to the d
 istribution shifts encountered in the real world.\n\nBio\nDamien Teney rec
 ently joined the Idiap Research Institute in Martigny as the head of the m
 achine learning group.\nDr. Teney was previously a research scientist at t
 he Australian Institute for Machine Learning at the University of Adelaide
 . He has also been affiliated with Carnegie Mellon University\, the Univer
 sity of Bath\, the University of Innsbruck\, and the University of Liege i
 n Belgium\, where he is originally from.\n\nMore information\n 
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420 https://epfl.zoom.us/
 j/66643876845?pwd=ck01YjFkTS9kUG91UEpLT1MwaU8wUT09
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR