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:20260805T205606Z
LOCATION:Room 403 A
DTSTART;TZID=America/Los_Angeles:20260723T160500
DTEND;TZID=America/Los_Angeles:20260723T161500
UID:siggraph_SIGGRAPH 2026_sess101_papers_1605@linklings.com
SUMMARY:MAViD: A Multimodal Framework for Audio-Visual Dialogue Understand
 ing and Generation
DESCRIPTION:Youxin Pang (Tsinghua University); Jiajun Liu, Lingfeng Tan, Y
 ong Zhang, and Feng Gao (meituan); Xiang Deng (Tsinghua University); Zhuol
 iang Kang and Xiaoming Wei (meituan); and Yebin Liu (Tsinghua University)\
 n\nMAViD is a multimodal framework for interactive audio-visual dialogue. 
 Its Conductor-Creator architecture integrates multimodal understanding and
  reasoning into response generation. By combining AR and diffusion models,
  MAViD enables synchronized, long-duration audio-video generation with con
 sistent identity and timbre, delivering vivid and contextually coherent di
 gital human interactions.\n\nInterest Area: Research & Education\n\nKeywor
 d: Animation, Artificial Intelligence/Machine Learning, Games, Generative 
 AI, Geometry, Modeling, Simulation\n\nRegistration Category: Full Conferen
 ce Supporter, Full Conference\n\nSession Chair: Przemyslaw Musialski (New 
 Jersey Institute of Technology (NJIT))\n\n
END:VEVENT
END:VCALENDAR