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 220-222
DTSTART;TZID=America/Los_Angeles:20250813T145000
DTEND;TZID=America/Los_Angeles:20250813T150000
UID:siggraph_SIGGRAPH 2025_sess154_papers_407@linklings.com
SUMMARY:SkillMimic-V2: Learning Robust and Generalizable Interaction Skill
 s from Sparse and Noisy Demonstrations
DESCRIPTION:Runyi Yu (Hong Kong University of Science and Technology, Shan
 ghai Aritificial Intelligence Laboratory); Yinhuai Wang, Qihan Zhao, and H
 ok Wai Tsui (Hong Kong University of Science and Technology); Jingbo Wang 
 (Shanghai Aritificial Intelligence Laboratory); and Ping Tan and Qifeng Ch
 en (Hong Kong University of Science and Technology)\n\nThis work addresses
  the challenge of learning robust interaction skills from limited demonstr
 ations. By introducing novel data augmentation techniques for skill transi
 tions and recovery patterns, combined with enhanced reinforcement imitatio
 n learning methods, we achieve superior performance in learning interactio
 n skills, demonstrating improved generalization and recovery capabilities 
 across diverse manipulation tasks.\n\nInterest Area: Research & Education\
 n\nRecording: Livestreamed, Not Livestreamed, Recorded, Not Recorded\n\nRe
 gistration Category: Full Conference, Virtual Access, Wednesday\n\n
END:VEVENT
END:VCALENDAR