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 220-222
DTSTART;TZID=America/Los_Angeles:20250813T164500
DTEND;TZID=America/Los_Angeles:20250813T165500
UID:siggraph_SIGGRAPH 2025_sess156_papers_1047@linklings.com
SUMMARY:Diffuse-CLoC: Guided Diffusion for Physics-based Character Look-ah
 ead Control
DESCRIPTION:Xiaoyu Huang (University of California Berkeley, Robotics and 
 AI Institute); Takara Truong (Stanford University, Robotics and AI Institu
 te); Yunbo Zhang, Fangzhou Yu, Jean Pierre Sleiman, and Jessica Hodgins (R
 obotics and AI Institute); Koushil Sreenath (Robotics and AI Institute, Un
 iversity of California Berkeley); and Farbod Farshidian (Robotics and AI I
 nstitute)\n\nMeet Diffuse-CLoC—a powerful unification of intuitive steerin
 g in kinematic motion generation and physics-based character control. By g
 uiding diffusion over joint state-action spaces, it enables agile, steerab
 le, and physically realistic motions across diverse downstream tasks—from 
 obstacle avoidance to task-space control and motion in-betweening—all from
  a single model, with no fine-tuning required.\n\nInterest Area: Research 
 & Education\n\nRecording: Livestreamed, Not Livestreamed, Recorded, Not Re
 corded\n\nRegistration Category: Full Conference, Virtual Access, Wednesda
 y\n\nSession Chair: Yuting Ye (Reality Labs Research, Meta; Meta)\n\n
END:VEVENT
END:VCALENDAR