BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.adass.org//adass2026//speaker//EFNFNM
BEGIN:VTIMEZONE
TZID:AWST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1;UNTIL=20051231T160000Z
TZNAME:AWST
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
END:STANDARD
BEGIN:STANDARD
DTSTART:20070325T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:AWST
TZOFFSETFROM:+0900
TZOFFSETTO:+0800
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20071028T030000
RRULE:FREQ=YEARLY;BYDAY=4SU;BYMONTH=10;UNTIL=20081025T190000Z
TZNAME:AWDT
TZOFFSETFROM:+0800
TZOFFSETTO:+0900
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-adass2026-HYLWYE@pretalx.adass.org
DTSTART;TZID=AWST:20261103T134500
DTEND;TZID=AWST:20261103T141500
DESCRIPTION:Radio astronomy is undergoing a transition in which efficient e
 xtraction of scientific information from ever-larger data volumes\, rather
  than data acquisition\, is becoming the limiting factor. The Square Kilom
 etre Array\, the next-generation Very Large Array\, and the ALMA Wideband 
 Sensitivity Upgrade will produce data at rates that make human inspection\
 , and even human labelling\, impractical. In this invited review we argue 
 that self-supervised representation learning provides a general framework 
 for applying artificial intelligence (AI) across the entire radio data lif
 ecycle: from visibilities\, through image reconstruction and large-scale s
 urvey analysis\, to exploration and anomaly detection at the scale of an o
 bservatory archive. We illustrate this with existing work on self-supervis
 ed learning methods and foundation models\, particularly in the radio doma
 in. We then describe how these ideas could be extended to the observatory 
 level through activities at the NSF–Simons AI Institute for Cosmic Origi
 ns (CosmicAI). We close with lessons learned\, open challenges\, and the n
 eed for shared radio datasets\, benchmarks\, and foundation models.
DTSTAMP:20261015T124103Z
LOCATION:Banquet Hall
SUMMARY:Learning the Radio Sky: Representation Learning from Visibilities t
 o Data Archives - Omkar Bait
URL:https://pretalx.adass.org/adass2026/talk/HYLWYE/
END:VEVENT
END:VCALENDAR