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:20240626T180035Z
LOCATION:3004\, 3rd Floor
DTSTART;TZID=America/Los_Angeles:20240626T143000
DTEND;TZID=America/Los_Angeles:20240626T144500
UID:dac_DAC 2024_sess145_RESEARCH781@linklings.com
SUMMARY:EMOGen: Enhancing Mask Optimization via Pattern Generation
DESCRIPTION:Research Manuscript\n\nSu Zheng (The Chinese University of Hon
 g Kong), Yuzhe Ma (The Hong Kong University of Science and Technology (Gua
 ngzhou)), and Bei Yu and Martin Wong (The Chinese University of Hong Kong)
 \n\nLayout pattern generation via deep generative models is a promising me
 thodology for building practical large-scale pattern libraries. \nHowever,
  although improving optical proximity correction (OPC) is a major target o
 f existing pattern generation methods, they are not explicitly trained for
  OPC and integrated into OPC methods. \nIn this paper, we propose EMOGen t
 o enable the co-evolution of layout pattern generation and learning-based 
 OPC methods. \nWith the novel co-evolution methodology, we achieve up to 3
 9% enhancement in OPC and 34% improvement in pattern legalization.\n\nTopi
 c: Design\n\nKeyword: Design for Manufacturability and Reliability\n\nSess
 ion Chairs: Shao-Yun Fang (National Taiwan University of Science and Techn
 ology) and Biying Xu (The Hong Kong University of Science and Technology (
 Guangzhou))
END:VEVENT
END:VCALENDAR