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:20260805T205608Z
LOCATION:Room 403 A
DTSTART;TZID=America/Los_Angeles:20260720T144000
DTEND;TZID=America/Los_Angeles:20260720T145000
UID:siggraph_SIGGRAPH 2026_sess109_papers_352@linklings.com
SUMMARY:EchoAvatar: Real-time Generative Avatar Animation from Audio Strea
 ms
DESCRIPTION:Bohong Chen, Yumeng Li, Yinglin Xu, Youyi Zheng, Yanlin Weng, 
 and Kun Zhou (State Key Laboratory of CAD & CG, Zhejiang University)\n\nWe
  introduce a novel framework designed to generate continuous, coherent ful
 l-body motion from arbitrary audio streams with low latency. Our approach 
 is a unified streaming architecture capable of synthesizing continuous mot
 ion from incremental audio inputs. And it serves as a plug-and-play soluti
 on for transforming voice agents into interactive humanoid avatars.\n\nInt
 erest Area: Research & Education\n\nKeyword: Animation, Artificial Intelli
 gence/Machine Learning, Generative AI, Geometry, Modeling, Simulation\n\nR
 egistration Category: Full Conference Supporter, Full Conference\n\nSessio
 n Chair: Derek Bradley (Walt Disney Company, Switzerland)\n\n
END:VEVENT
END:VCALENDAR
