Abstract

Current AI systems fail when encountering unfamiliar situations. This talk presents a unified approach where synthesis models help analysis models handle new scenarios by transforming unfamiliar inputs into recognizable forms. We demonstrate a generative world model that creates mental simulations from single images, enabling navigation through imagined environments. This supports sophisticated reasoning for safety-critical decisions. The approach represents progress toward AI that generalizes beyond training data by using generation to bridge unfamiliar and familiar scenarios.

Advisors

Prof. Alan Yuille