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:20260805T205604Z
LOCATION:Room 403  B
DTSTART;TZID=America/Los_Angeles:20260720T145000
DTEND;TZID=America/Los_Angeles:20260720T150000
UID:siggraph_SIGGRAPH 2026_sess120_papers_744@linklings.com
SUMMARY:Locality-Aware Automatic Differentiation on the GPU for Mesh-Based
  Computations
DESCRIPTION:Ahmed Mahmoud, Rahul Goel, Jonathan Ragan-Kelley, and Justin S
 olomon (Massachusetts Institute of Technology (MIT))\n\nWe present a GPU s
 ystem for automatic differentiation for functions defined on triangle mesh
 es that exploits locality and sparsity to deliver efficient derivative com
 putation. From simple user-defined energy terms, the system produces gradi
 ents, Jacobians, and sparse Hessians, accelerating simulation and optimiza
 tion workflows and shifting the computational bottleneck away from differe
 ntiation.\n\nInterest Area: Research & Education\n\nKeyword: Geometry, Har
 dware, Modeling, Rendering\n\nRegistration Category: Full Conference Suppo
 rter, Full Conference\n\nSession Chair: Tamy Boubekeur (Adobe)\n\n
END:VEVENT
END:VCALENDAR