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 301-305
DTSTART;TZID=America/Los_Angeles:20250811T080000
DTEND;TZID=America/Los_Angeles:20250811T084500
UID:siggraph_SIGGRAPH 2025_sess488_ftalk_103@linklings.com
SUMMARY:Talk: A Bottom-Up Approach to Intelligence
DESCRIPTION:Farbod Farshidian (RAI Institute)\n\nThe rise of Foundation Mo
 dels, including LLMs and VLMs, has brought us closer to creating AI agents
  that understand and act in the world. However, challenges remain, particu
 larly in the "act" component, due to the scarcity of human motion data and
  a lack of action labels. This talk focuses on building intelligence from 
 the ground up. Our main goal has been to achieve zero-shot sim-to-real tra
 nsfer on hardware with minimal human intervention by integrating reinforce
 ment learning and imitation learning into a streamlined motion imitation f
 ramework. We began by focusing on single-task policies and later expanded 
 to multi-task policies capable of generalizing across behaviors. This talk
  will showcase unprecedented natural behaviors in dynamic tasks performed 
 by the Boston Dynamics e-Atlas robot, marking a major advance in bridging 
 the gap between human characters in graphics and physical humanoid robots 
 in robotics.\n\nInterest Area: Research & Education\n\nRecording: Livestre
 amed, Recorded\n\nKeyword: Animation, Physical AI, Robotics\n\nRegistratio
 n Category: Full Conference, Virtual Access, Experience, Monday\n\n
END:VEVENT
END:VCALENDAR