BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.adass.org//adass2026//speaker//PCWQYJ
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-XRSQ3D@pretalx.adass.org
DTSTART;TZID=AWST:20261103T161500
DTEND;TZID=AWST:20261103T163000
DESCRIPTION:Radio interferometric imaging reconstructs sky brightness from 
 sparsely sampled Fourier measurements\, leading to a highly ill-posed inve
 rse problem that is increasingly challenged by the scale and resolution de
 mands of next-generation telescopes\, such as the Square Kilometre Array (
 SKA). Classical approaches\, including CLEAN and its variants\, often stru
 ggle with extended emission and face significant challenges in scaling to 
 high-throughput\, high-dynamic-range observations. We propose a data-drive
 n transformer-based radio interferometric imaging algorithm\, TransformerR
 IM\, that integrates learnt image priors with physics-based measurement co
 nstraints. The reconstruction module is built on a Swin Transformer encode
 r-decoder\, enabling multi-scale feature extraction and long-range spatial
  modelling. We further implement CUDA-based differentiable forward and adj
 oint operators for mapping between image space and irregularly sampled vis
 ibilities\, allowing residual visibility information to be incorporated in
 to recurrent reconstruction and end-to-end training. Uncertainty quantific
 ation is performed during inference by sampling perturbed visibilities fro
 m noise models\, reconstructing a set of possible images. The method is tr
 ained on simulated and real datasets from JVLA B-configuration and LOFAR. 
 On data of 3C 75 (a binary SMBH system)\, the inference result can achieve
  a dynamic range of 5.91M using our model\, compared to 3.01M using CLEAN.
  The trained model makes inference substantially faster than CLEAN. The ex
 perimental results demonstrate that TransformerRIM provides a scalable and
  reliable path toward high-efficiency\, high-dynamic-range radio imaging p
 ipelines for next-generation radio telescopes.
DTSTAMP:20261001T101731Z
LOCATION:Banquet Hall
SUMMARY:TransformerRIM: A Data-Driven Transformer-based Radio Interferometr
 ic Imager with Uncertainty Quantification - Qitong Anabel Tan
URL:https://pretalx.adass.org/adass2026/talk/XRSQ3D/
END:VEVENT
END:VCALENDAR