BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:66626533-3762-4231-b065-303437316337
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:New Advances in Safe and Efficient Large Language Models - Hon
 gyang Zhang\, Assistant Professor\, University of Waterloo
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20251102T090000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20231105T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20241103T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20230312T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20240310T020000
RDATE:20250309T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:6b02d710-92b3-40c2-b683-aaac28a3ab8e
DTSTAMP:20260305T230501Z
CLASS:PUBLIC
CREATED:20240206T214337Z
DESCRIPTION:Zoom Link Abstract: Recent strides in large language models (LL
 Ms) have underscored the critical importance of addressing both AI safety 
 and decoding efficiency. In the first segment of this talk\, we delve into
  the integration of self-evaluation and rewind mechanisms within unaligned
  LLMs\, presenting the Rewindable Auto-regressive INference (RAIN) framewo
 rk. RAIN empowers pre-trained LLMs to autonomously assess their own output
 s\, leveraging these evaluations to iteratively refine response generation
  through self-boosting. Notably\, this innovative approach enhances AI saf
 ety without…
DTSTART;TZID=America/Vancouver:20240221T110000
DTEND;TZID=America/Vancouver:20240221T120000
LAST-MODIFIED:20240220T193354Z
LOCATION:UBC Vancouver Campus\, ICCS X836 / Please register to receive Zoom
  link
SUMMARY:New Advances in Safe and Efficient Large Language Models - Hongyang
  Zhang\, Assistant Professor\, University of Waterloo
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/new-advances-safe-and-efficient-large-langua
 ge-models-hongyang-zhang-assistant-professor
END:VEVENT
END:VCALENDAR