BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250522T212740Z
LOCATION:Bluebird Ballroom
DTSTART;TZID=America/Denver:20240728T180000
DTEND;TZID=America/Denver:20240728T204500
UID:siggraph_SIGGRAPH 2024_sess211_papers_203@linklings.com
SUMMARY:MoConVQ: Unified Physics-based Motion Control via Scalable Discret
 e Representations
DESCRIPTION:Heyuan Yao and Zhenhua Song (School of Computer Science, Pekin
 g University); Yuyang Zhou (Peking University, School of EECS); Tenglong A
 o (School of Computer Science, Peking University); and Baoquan Chen and Li
 bin Liu (Peking University, State Key Laboratory of General Artificial Int
 elligence)\n\nWe present MoConVQ, a uniform framework enabling simulated a
 vatars to acquire diverse skills from large, unstructured datasets. Levera
 ging a rich and scalable discrete skill representation, MoConVQ supports a
  broad range of applications, including pose estimation, interactive contr
 ol, text-to-motion generation, and, more interestingly, integrating motion
  generation with Large Language Models (LLMs).\n\nInterest Area: Arts & De
 sign, Production & Animation, Research & Education\n\nRecording: Livestrea
 med, Recorded\n\nRegistration Category: Full Conference, Full Conference S
 upporter, Virtual Access, Experience, Exhibitor Full Conference, Exhibitor
  Experience, Sunday\n\n
END:VEVENT
END:VCALENDAR