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:20250811T093000
DTEND;TZID=America/Los_Angeles:20250811T094000
UID:siggraph_SIGGRAPH 2025_sess148_papers_396@linklings.com
SUMMARY:TokenVerse: Versatile Multi-concept Personalization in Token Modul
 ation Space
DESCRIPTION:Daniel Garibi (Tel Aviv University, DeepMind); Shahar Yadin (T
 echnion - Israel Institute of Technology, DeepMind); Roni Paiss, Omer Tov,
  Shiran Zada, and Ariel Ephrat (DeepMind); Tomer Michaeli (Technion - Isra
 el Institute of Technology, DeepMind); Inbar Mosseri (DeepMind); and Tali 
 Dekel (Weizmann Institute of Science, DeepMind)\n\nTokenVerse extracts com
 plex visual elements from images by identifying semantic directions in per
 -token modulation space of DiT models for each word in the image caption. 
 It's capable of combining concepts from multiple sources by adding corresp
 onding directions, enabling flexible generation of new combinations includ
 ing abstract concepts like lighting and poses.\n\nInterest Area: Research 
 & Education\n\nRecording: Livestreamed, Not Livestreamed, Recorded, Not Re
 corded\n\nRegistration Category: Full Conference, Virtual Access, Monday\n
 \nSession Chair: Ali Mahdavi-Amiri (Simon Fraser University, MARZ VFX)\n\n
END:VEVENT
END:VCALENDAR