BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Multimodal Foundation Models and Agents for Biological Discovery a
 nd Personalized Therapeutics
DTSTART:20250722T103000
DTEND:20250722T123000
DTSTAMP:20260416T191435Z
UID:9c4491de72084a9fc065cbe9b2cf772d287f840c07c47ee3ef32d33a
CATEGORIES:Conferences - Seminars
DESCRIPTION:Eeshaan Jain\nEDIC candidacy exam\nExam president: Prof. Marti
 n Jaggi\nThesis advisor: Prof. Charlotte Bunne\nCo-examiner: Dr Dorina Tha
 nou\n\nAbstract\nThis research aims to develop machine learning methods th
 at enable robust\, efficient\, and personalized decision-making in biomedi
 cal settings. The work focuses on three interconnected directions. First\,
  I will develop foundation models for high-dimensional tissue data—su
 ch as histopathology and multiplexed imaging—that learn unified repre
 sentations by integrating spatial\, morphological\, and molecular signals.
  These models are designed to generalize across data modalities and serve 
 as a basis for downstream tasks. Second\, I will explore test-time adaptat
 ion under constrained settings\, where only partial input is available. By
  learning strategies for sequential feature acquisition\, the goal is to m
 aintain diagnostic accuracy while minimizing cost and information redundan
 cy. Third\, I will extend these methods toward the development of AI agent
 s capable of structured reasoning across heterogeneous data sources. These
  agents will support personalized therapeutic recommendations by combining
  model outputs with contextual and external knowledge. Together\, this wor
 k contributes toward building adaptive\, scalable\, and clinically relevan
 t AI systems for precision medicine.\n\nSelected papers\ncoming soon
LOCATION:BC 200 https://plan.epfl.ch/?room==BC%20200
STATUS:CANCELLED
END:VEVENT
END:VCALENDAR