Abstract

Abstract: Today’s language models are increasingly capable of reasoning over multiple steps with verification and backtracking to solve challenging problems. However, multimodal reasoning models that can reason over an integrated set of modalities such as text, images, audio, video, and knowledge graphs are sorely lacking, and can pave the way for a next frontier of AI. I will describe our group’s work on advancing the frontiers of multimodal reasoning, from new multimodal reasoning benchmarks to training multimodal foundation models with modern reasoning approaches, and applications to social understanding and education.

Bio: Paul Liang is an Assistant Professor at the MIT Media Lab and MIT EECS . His research advances the foundations of multisensory artificial intelligence to enhance the human experience. He is a recipient of the Siebel Scholars Award, Waibel Presidential Fellowship, Facebook PhD Fellowship, Center for ML and Health Fellowship, Rising Stars in Data Science, and 3 best paper awards. Outside of research, he received the Alan J. Perlis Graduate Student Teaching Award for developing new courses on multimodal machine learning.