BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://www.dfp.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:33323738-6530-4935-a364-343866353430
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:Recent Development of Generative AI Focused on Computer Vision
  - Dongjun Kim\, Postdoctoral Scholar\, Stanford University
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20261101T090000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20241103T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20251102T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20240310T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20250309T020000
RDATE:20260308T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:90368d72-b77e-48ad-9424-38a3b6b764e2
DTSTAMP:20260109T045822Z
CLASS:PUBLIC
CREATED:20241121T233427Z
DESCRIPTION:Abstract: With the recent advancements in diffusion models\, th
 e image generation problem has become nearly resolved in terms of quality.
  However\, because most large language models (LLMs) are built on autoregr
 essive transformer architectures\, there remains a significant gap between
  LLMs and diffusion models\, and it is challenging to combine text generat
 ion and image/video/audio generation in a single unified model. This talk 
 will explore recent efforts to bridge this gap.
DTSTART;TZID=America/Vancouver:20241209T140000
DTEND;TZID=America/Vancouver:20241209T150000
LAST-MODIFIED:20241121T233953Z
LOCATION:UBC Vancouver Campus\, ICCS X836
SUMMARY:Recent Development of Generative AI Focused on Computer Vision - Do
 ngjun Kim\, Postdoctoral Scholar\, Stanford University
TRANSP:OPAQUE
URL:https://www.dfp.ubc.ca/index.php/event/recent-development-generative-ai
 -focused-computer-vision-dongjun-kim-postdoctoral-scholar
END:VEVENT
END:VCALENDAR