Keynote

Open-source Multimodal AI

Friday, May 29

17:40 - 18:40

RoomsSpaghetti, Lasagna, Tagliatelle, Pizza, Piadina, Recruiting, Tigelle, Tortellini, Gnocchi, Passatelli

LanguageEnglish

Abstract

In this talk Merve will walk through how to get started with open-source multimodal models, the state-of-the-art, the tools and more, covering from computer use agents to OCR models.

MERVE NOYAN

Merve works in the open-source team at Hugging Face. She works on everything multimodality (vision language models), agents and computer vision. She’s also the author of the book Vision Language Models by O’Reilly.