BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//program.berlinbuzzwords.de//bbuzz26//speaker//WSF7G8
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-bbuzz26-QJBKUU@program.berlinbuzzwords.de
DTSTART;TZID=CET:20260609T140000
DTEND;TZID=CET:20260609T144000
DESCRIPTION:When users expect alerts for new products matching an uploaded 
 image\, the problem becomes inverse hybrid search. Unlike top-K search\, a
 lerting must guarantee fetch-all semantics: zero missed matches across all
  saved searches\, combining vector similarity\, boolean filters\, and lexi
 cal signals. We show why this breaks traditional scaling intuition.
DTSTAMP:20260525T074946Z
LOCATION:Kesselhaus
SUMMARY:The Three-Body Problem of Inverse Hybrid Search - Ravindra Harige
URL:https://program.berlinbuzzwords.de/bbuzz26/talk/QJBKUU/
END:VEVENT
END:VCALENDAR