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:20260417T190157Z
LOCATION:West Building\, Rooms 118-120
DTSTART;TZID=America/Los_Angeles:20250811T094000
DTEND;TZID=America/Los_Angeles:20250811T095000
UID:siggraph_SIGGRAPH 2025_sess148_papers_415@linklings.com
SUMMARY:Dynamic Concepts Personalization from Single Videos
DESCRIPTION:Rameen Abdal, Or Patashnik, Ivan Skorokhodov, Willi Menapace, 
 Aliaksandr Siarohin, Sergey Tulyakov, Daniel Cohen-Or, and Kfir Aberman (S
 nap)\n\nPersonalizing text-to-video models is challenging because dynamic 
 concepts require capturing both appearance and motion. We propose Set-and-
 Sequence, a framework that personalizes DiT-based video models by first le
 arning an identity LoRA basis from unordered frames, then fine-tuning coef
 ficients with motion residuals on full videos, enabling superior editabili
 ty and compositionality for applications.\n\nInterest Area: Research & Edu
 cation\n\nRecording: Livestreamed, Not Livestreamed, Recorded, Not Recorde
 d\n\nRegistration Category: Full Conference, Virtual Access, Monday\n\nSes
 sion Chair: Ali Mahdavi-Amiri (Simon Fraser University, MARZ VFX)\n\n
END:VEVENT
END:VCALENDAR