BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME:Accelerating Biomedical Discoveries through Responsible Multim
 odal Learning
X-WR-TIMEZONE:Pacific Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20260518T215940Z
UID:tag:localist.com\,2008:EventInstance_52084167484563
DTSTART:20260306T220000Z
DTEND:20260306T230000Z
DESCRIPTION:Watch the recording here\n\n \n\nZoom.\n\nDate: March 6\n\nTime
 : 2 p.m.\n\nLocation: LINC 268\n\n \n\nAbstract: The rapid growth of multi
 modal biomedical data — spanning imaging\, genomics\, clinical text\, an
 d molecular structures — presents unprecedented opportunities for advanc
 ing scientific discovery. However\, effectively integrating these heteroge
 neous data sources remains a fundamental challenge. In this talk\, I will 
 present our recent work addressing novel challenges in multimodal biomedic
 al learning. First\, I will introduce our framework for flexible and adapt
 ive multimodal learning\, designed to operate with any arbitrary combinati
 on of modalities. Unlike conventional approaches that assume fixed modalit
 y availability\, our method gracefully handles missing\, incomplete\, or d
 ynamically varying inputs\, making it well-suited for real-world clinical 
 and research settings where data availability is often unpredictable. Seco
 nd\, I will discuss our efforts toward responsible multimodal learning gui
 ded by biological priors\, ensuring that model behavior aligns with establ
 ished domain knowledge and yields interpretable\, trustworthy predictions.
  By embedding biological constraints into the learning process\, we can im
 prove generalization\, reduce spurious correlations\, and promote scientif
 ic rigor. Together\, these contributions point toward a future where multi
 modal AI systems can reliably and responsibly accelerate biomedical discov
 eries.\n\nBio: Tianlong Chen is an assistant professor in the Department o
 f Computer Science at the University of North Carolina at Chapel Hill and 
 is the Chief AI Scientist at hireEZ. He received his Ph.D. degree from ECE
  at UT Austin in 2023 and had a postdoc at MIT and Harvard in 2024. His re
 search focuses on efficient and reliable machine learning\, large language
  model agents\, multimodal learning\, and AI for BioScience. He received t
 he Meta Research Award\, Amazon Research Award\, Cisco Faculty Award\, IBM
 -UNC Junior Faculty Development Award\, and several best/outstanding paper
  awards from various conferences and workshops like SIGBio\, NAACL\, LoG\,
  AMIA\, ACM MM\, AAAI\, NeurIPS\, etc. He regularly serves as conference (
 senior) area chairs\, journal editors\, invited speakers\, tutorial/worksh
 op organizers\, various panelist positions\, and reviewers. His research i
 s gratefully supported by NIH\, NSF\, DOE\, as well as dozens of industry 
 and university grants.
GEO:44.565762;-123.281717
LOCATION:Learning Innovation Center (LINC)\, 268
SUMMARY:Accelerating Biomedical Discoveries through Responsible Multimodal 
 Learning
URL;VALUE=URI:https://events.oregonstate.edu/event/accelerating-biomedical-
 discoveries-through-responsible-multimodal-learning
CATEGORIES:Lecture or Presentation
END:VEVENT
END:VCALENDAR