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 403  B
DTSTART;TZID=America/Los_Angeles:20260722T141000
DTEND;TZID=America/Los_Angeles:20260722T142000
UID:siggraph_SIGGRAPH 2026_sess184_papers_678@linklings.com
SUMMARY:SharpNet: Enhancing MLPs to Represent Functions with Controlled No
 n-differentiability
DESCRIPTION:Hanting Niu (Institute of Software, Chinese Academy of Science
 s; University of Chinese Academy of Sciences); Junkai Deng (Nanyang Techno
 logical University); Fei Hou and Wencheng Wang (Institute of Software, Chi
 nese Academy of Sciences; University of Chinese Academy of Sciences); and 
 Ying He (Nanyang Technological University)\n\nWe propose SharpNet, an enha
 nced MLP architecture that augments the input with a feature function to p
 roduce controllable derivative jumps. We show that SharpNet can preserve t
 he sharpness in the intended regions while maintaining smoothness elsewher
 e, and that it outperforms baseline methods in sharpness-critical tasks su
 ch as CAD reconstruction.\n\nInterest Area: Research & Education\n\nKeywor
 d: Artificial Intelligence/Machine Learning, Geometry, Modeling\n\nRegistr
 ation Category: Full Conference Supporter, Full Conference\n\nSession Chai
 r: Nicholas Sharp (NVIDIA)\n\n
END:VEVENT
END:VCALENDAR