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:20260402T024534Z
LOCATION:Level 2 Lobby
DTSTART;TZID=America/Los_Angeles:20250623T180000
DTEND;TZID=America/Los_Angeles:20250623T190000
UID:dac_DAC 2025_sess287_LBR103@linklings.com
SUMMARY:Late Breaking Results: Encoder-Decoder Generative Diffusion Transf
 ormer Towards Push-Button Analog IC Sizing
DESCRIPTION:Filipe Azevedo, Nuno Lourenco, and Ricardo Martins (Universida
 de de Lisboa)\n\nIn this paper, disruptive research using generative diffu
 sion models (DMs) with an attention-based encoder-decoder backbone is cond
 ucted to automate the sizing of analog integrated circuits (ICs). Unlike t
 ime-consuming optimization-based methods, the encoder-decoder DM is able t
 o sample accurate solutions at push-button speed by solving the inverse si
 zing problem. Experimental results show that the proposed model outperform
 s the most recent deep learning-based techniques, presenting higher genera
 lization capabilities to performance targets not seen during training.\n\n
END:VEVENT
END:VCALENDAR