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:20220715T000420Z
LOCATION:3007\, Level 3
DTSTART;TZID=America/Los_Angeles:20220714T113700
DTEND;TZID=America/Los_Angeles:20220714T120000
UID:dac_DAC 2022_sess117_RESEARCH126@linklings.com
SUMMARY:Generic Lithography Modeling with Dual-band Optics-Informed Neural
  Networks
DESCRIPTION:Research Manuscript\n\nGeneric Lithography Modeling with Dual-
 band Optics-Informed Neural Networks\n\nYang, Li, Sastry, Mukhopadhyay, Ki
 lgard...\n\nLithography simulation is a critical step in VLSI design for m
 anufacturability.\nLegacy solutions with rigorous models are time consumin
 g when seeking high simulation accuracy even equipped with various approxi
 mation techniques. Although machine learning solutions are investigated re
 cently, these learning-based methods are either having limited usage scena
 rio or lacking in modeling accuracy. To tackle these concerns, we present 
 a dual-band neural network design that is compliant with optical physics b
 eneath lithography, allows via/metal layer contour simulation at 1nmX1nm p
 ixel resolution with any tile size. The model is 10X smaller than existing
  solutions when achieving even much better contour generation results.\n\n
 Topic: EDA\n\nKeyword: Physical Design and Verification, Lithography and D
 FM
END:VEVENT
END:VCALENDAR