BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:33343237-3337-4261-b537-663233353932
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:Efficient and Long-Context GenAI Models - Sung Ju Hwang\, KAIS
 T Endowed Chair Professor\, Kim Jaechul School of Artificial Intelligence 
 and School of Computing at KAIST
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20260308T100000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20231105T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20241103T020000
RDATE:20251102T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20240310T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20250309T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:9505310b-4056-4e7d-84cb-6d673490eda8
DTSTAMP:20260501T044615Z
CLASS:PUBLIC
CREATED:20240621T211634Z
DESCRIPTION:Zoom Link Abstract: Generative AI models have demonstrated rema
 rkable performance across various tasks in recent years. However\, their d
 eployment in real-world production-grade AI systems is hindered by signifi
 cant computational costs. Additionally\, these models are constrained by t
 heir limited context window size\, which restricts their ability to handle
  more complex tasks that require larger working memory. In this talk\, I w
 ill present recent advancements from our group aimed at addressing these c
 hallenges in generative AI models. Specifically\, I will discuss methods t
 o improve training and…
DTSTART;TZID=America/Vancouver:20240626T100000
DTEND;TZID=America/Vancouver:20240626T110000
LAST-MODIFIED:20240621T213338Z
LOCATION:UBC Vancouver Campus\, ICCS X836 / Zoom
SUMMARY:Efficient and Long-Context GenAI Models - Sung Ju Hwang\, KAIST End
 owed Chair Professor\, Kim Jaechul School of Artificial Intelligence and S
 chool of Computing at KAIST
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/efficient-and-long-context-genai-models-sung
 -ju-hwang-kaist-endowed-chair-professor-kim
END:VEVENT
END:VCALENDAR