AI Center Seminar - AI for Health series - Prof. Michael Moor

The talk is jointly organized by the EPFL AI Center and the Fellay Lab – Human Genomics of Infection and Immunity.

Hosts: Prof. Jacques Fellay & Dr. Dorina Thanou

The talk will be held on-site only. For logistical purposes, please use the following form to register (with your EPFL email address): Here. 

The talk will be followed by a coffee session.

_________________
Title
Tool-augmented medical reasoning

Abstract
The exceptionally rapid development of highly flexible and reusable artificial intelligence (AI) models—often referred to as foundation models (FMs)—is likely to usher in newfound capabilities across the medical domain. In this talk, we will discuss medical FMs and the multimodal AI agents we can build on top, highlighting key desiderata and pitfalls of such systems. Moreover, we will explore novel evaluation strategies, as well as new ways to augment medical AI agents with tools and up-to-date medical information.

Bio
Michael Moor, MD, PhD recently joined ETH Zurich as an Assistant Professor of Medical AI in the Department of Biosystems Science and Engineering (D-BSSE). Previously, he pursued postdoctoral research at Stanford University’s Department of Computer Science, mentored by Prof. Jure Leskovec. He earned his PhD in the Machine Learning and Computational Biology Lab, advised by Prof. Karsten Borgwardt, and holds an MD from the University of Basel. His research focuses on developing medical foundation models and language agents that can flexibly handle multiple data modalities—such as images, text, and time series—and are capable of learning to solve new tasks on the fly. His work has been published in flagship journals like Nature and Nature Medicine, and presented at leading AI conferences, including NeurIPS, ICML, EMNLP, and ICLR. He is a recipient of the fellowship of the Swiss Study Foundation.