Harvard Medical AI: Sameer Sundrani presents Oscar: ... Pre-training for Vision-Language Tasks

A reading group session as part of the Rajpurkar Lab at Harvard which works on developing medical AI. Each week, a lab member covers a recent paper in either core AI or medical AI in a format targeted to be broadly interesting to those interested in the cutting edge of AI and its applications in medicine. In this session, lab member Sameer Sundrani presents “Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks“ Full Paper: Rajpurkar Lab Website: Subscribe to get weekly updates.