Event Speaker
Pranav Rajpurkar, PhD
Associate Professor of Biomedical Informatics
Harvard Medical School
Sessions
VLMs in Action: Teaching Machines to See and Speak Imaging
Presented by Cody H. Savage, MD, Pranav Rajpurkar, PhD, Raffi Salibian, MD Jun 10, 2026 | 1:45 PM.
Vision-language models (VLMs) are emerging as powerful tools that combine visual understanding with natural language capabilities, offering new opportunities for clinical support, workflow efficiency, and research innovation. This session provides an accessible overview of what VLMs are, how they differ from traditional AI approaches, and where they can add value in imaging environments. Presenters will…