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 211-214
DTSTART;TZID=America/Los_Angeles:20250814T090000
DTEND;TZID=America/Los_Angeles:20250814T091000
UID:siggraph_SIGGRAPH 2025_sess122_papers_1111@linklings.com
SUMMARY:GAIA: Generative Animatable Interactive Avatars with Expression-co
 nditioned Gaussians
DESCRIPTION:Zhengming Yu (Texas A&M University); Tianye Li (NVIDIA); Jingx
 iang Sun (Tsinghua University, NVIDIA); Omer Shapira, Seonwook Park, Micha
 el Stengel, and Matthew Chan (NVIDIA); Xin Li and Wenping Wang (Texas A&M 
 University); and Koki Nagano and Shalini De Mello (NVIDIA)\n\nWe present G
 AIA (Generative Animatable Interactive Avatars) for high-fidelity 3D head 
 avatar generation. GAIA learns dynamic details with expression-conditioned
  Gaussians, while being animatable consistently with an underlying morphab
 le model. With a novel two-branch architecture, GAIA disentangles identity
  and expression. GAIA achieves state-of-the-art realism and supports inter
 active rendering and animation.\n\nInterest Area: Research & Education\n\n
 Recording: Livestreamed, Not Livestreamed, Recorded, Not Recorded\n\nRegis
 tration Category: Full Conference, Virtual Access, Thursday\n\nSession Cha
 ir: Abhimitra Meka (Google)\n\n
END:VEVENT
END:VCALENDAR