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:20260805T205607Z
LOCATION:Room 403  B
DTSTART;TZID=America/Los_Angeles:20260722T145000
DTEND;TZID=America/Los_Angeles:20260722T150000
UID:siggraph_SIGGRAPH 2026_sess184_papers_789@linklings.com
SUMMARY:Generative Modeling with Orbit-Space Particle Flow Matching
DESCRIPTION:Sinan Wang, Jinjin He, Shenyifan Lu, Ruicheng Wang, Greg Turk,
  and Bo Zhu (Georgia Institute of Technology)\n\nOrbit-Space Geometric Pro
 bability Paths (OGPP) is a flow-matching framework for generative modeling
  of particle systems that exploits shared geometric structure and uses pro
 bability path geometry to encode geometric information. It enables high-qu
 ality, efficient generation of particle configurations and point-cloud sur
 faces with normals, achieving state-of-the-art performance across diverse 
 generation tasks.\n\nInterest Area: Research & Education\n\nKeyword: Artif
 icial Intelligence/Machine Learning, Geometry, Modeling\n\nRegistration Ca
 tegory: Full Conference Supporter, Full Conference\n\nSession Chair: Nicho
 las Sharp (NVIDIA)\n\n
END:VEVENT
END:VCALENDAR