BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:63343662-3734-4536-b862-356634386565
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:Exploring Trustworthy Foundation Models: Benchmarking\, Finetu
 ning and Reasoning - Bo Han\, Associate Professor\, Hong Kong Baptist Univ
 ersity
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20270314T100000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20241103T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20251102T020000
RDATE:20261101T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20250309T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20260308T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:ef1b1e10-b00c-44a1-bb35-5a93d71b238a
DTSTAMP:20260123T134224Z
CLASS:PUBLIC
CREATED:20250704T222712Z
DESCRIPTION:Abstract: In the current landscape of machine learning\, where 
 foundation models must navigate imperfect real-world conditions such as no
 isy data and unexpected inputs\, ensuring their trustworthiness through ri
 gorousbenchmarking\, safety-focused finetuning\, and robust reasoning is m
 ore critical than ever. In this talk\, I will focus on three recent resear
 ch advancements that collectively advance these dimensions\, offering a co
 mprehensive approach to building trustworthy foundation models. For benchm
 arking\, I will introduce CounterAnimal\, a dataset designed to systematic
 ally evaluate CLIP’s…
DTSTART;TZID=America/Vancouver:20250715T113000
DTEND;TZID=America/Vancouver:20250715T123000
LAST-MODIFIED:20250704T223309Z
LOCATION:UBC Vancouver Campus\, Fried Kaiser (KAIS) building\, Room 2020/20
 30\, 2332 Main Mall
SUMMARY:Exploring Trustworthy Foundation Models: Benchmarking\, Finetuning 
 and Reasoning - Bo Han\, Associate Professor\, Hong Kong Baptist Universit
 y
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/exploring-trustworthy-foundation-models-benc
 hmarking-finetuning-and-reasoning-bo-han
END:VEVENT
END:VCALENDAR