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:20260805T205601Z
LOCATION:Room 408 B
DTSTART;TZID=America/Los_Angeles:20260720T091000
DTEND;TZID=America/Los_Angeles:20260720T092000
UID:siggraph_SIGGRAPH 2026_sess127_papers_1102@linklings.com
SUMMARY:Learning Laplacian Eigenspace with Mass-Aware Neural Operators on 
 Point Clouds
DESCRIPTION:Zherui Yang (University of Science and Technology of China); T
 ao Du (Tsinghua University, Shanghai Qi Zhi Institute); and Ligang Liu (Un
 iversity of Science and Technology of China)\n\nNEO is a neural framework 
 for fast Laplace-Beltrami spectral analysis on 3D point clouds. Rather tha
 n computing eigenvectors with expensive iterative solvers, it predicts low
 -frequency eigenspaces directly from geometry, enabling near-linear scalin
 g, robustness to irregular sampling, and accurate zero-shot transfer to su
 bstantially higher-resolution shapes and downstream spectral tasks.\n\nInt
 erest Area: Research & Education\n\nKeyword: Artificial Intelligence/Machi
 ne Learning, Geometry, Modeling, Simulation\n\nRegistration Category: Full
  Conference Supporter, Full Conference\n\nSession Chair: Yiying Tong (Mich
 igan State University)\n\n
END:VEVENT
END:VCALENDAR