BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260417T190158Z
LOCATION:West Building\, Rooms 118-120
DTSTART;TZID=America/Los_Angeles:20250813T164500
DTEND;TZID=America/Los_Angeles:20250813T165500
UID:siggraph_SIGGRAPH 2025_sess142_papers_297@linklings.com
SUMMARY:IP-Composer: Semantic Composition of Visual Concepts
DESCRIPTION:Sara Dorfman and Dana Cohen-Bar (Tel Aviv University), Rinon G
 al (NVIDIA), and Daniel Cohen-Or (Tel Aviv University)\n\nIP-Composer is a
  novel, training-free method for compositional image generation from multi
 ple reference images. Extending IP-Adapter, it uses natural language to id
 entify concept-specific subspaces in CLIP, projects input images into thes
 e subspaces to extract targeted concepts, and fuses them into composite em
 beddings—enabling fine-grained, controllable generation across diverse vis
 ual concepts.\n\nInterest Area: Research & Education\n\nRecording: Livestr
 eamed, Not Livestreamed, Recorded, Not Recorded\n\nRegistration Category: 
 Full Conference, Virtual Access, Wednesday\n\nSession Chair: Valentin Desc
 haintre (Adobe Research)\n\n
END:VEVENT
END:VCALENDAR