BEGIN:VCALENDAR
PRODID:-//github.com/ical-org/ical.net//NONSGML ical.net 4.0//EN
VERSION:2.0
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:STANDARD
DTSTART:20241103T020000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250309T020000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
DESCRIPTION:Abstract: Deep learning models have achieved expert-level perf
 ormance in diagnosing various ophthalmic conditions using imaging modalit
 ies like color fundus photography (CFP). However\, these models operate u
 nder the assumption that the training and test data are drawn from an ide
 ntical distribution1. When this assumption is violated by covariate shift
 s (e.g.\, varying imaging protocols\, camera hardware\, field-of-view dif
 ferences\, patient demographics)\, performance degrades substantially. Un
 supervised Domain Adaptation (UDA) addresses this problem by adapting mod
 els using unlabeled target data. Existing UDA approaches typically align 
 feature distributions using adversarial learning or entropy-based objecti
 ves driven by softmax probabilities. However\, softmax normalizes logit m
 agnitudes\, which may obscure distributional shifts and cause falsely ove
 rconfident predictions. In this study\, we propose Class-Conditional Ener
 gy Alignment\, which adapts source-trained classifiers by matching energy
  computed directly from unnormalized logits across source and target doma
 ins. Younjoon Chung is a Ph.D. student in Computational Biology and Biome
 dical Informatics (CBB) at Yale University\, advised by Prof. Qingyu Chen
  and Prof. Lucila Ohno-Machado . His research interests lie in the inters
 ection of machine learning\, computer vision and healthcare. Specifically
 \, focusing on developing robust domain adaptation techniques to ensure m
 edical AI models can generalize across diverse clinical environments\, in
 cluding variations in patient populations\, imaging hardware\, etc.\n\nSp
 eaker:\nYounjoon Chung\n\nAdmission:\nFree\n\nDetails URL:\nhttps://medic
 ine.yale.edu/event/nlpllm-interest-group-35/\n
DTEND;TZID=America/New_York:20260511T170000
DTSTAMP:20260514T200745Z
DTSTART;TZID=America/New_York:20260511T160000
LOCATION:Virtual - Join our mailing list to receive Zoom Passcode: https:/
 /mailman.yale.edu/mailman/listinfo/nlp-llm-ig \, URL: https://yale.zoom.u
 s/j/93599941969
SEQUENCE:0
STATUS:Confirmed
SUMMARY:NLP/LLM Interest Group
UID:5fd3eae1-957b-477e-a46d-ef1e890362f9
END:VEVENT
END:VCALENDAR