What is representational alignment? How can we use it to study or improve intelligent systems? What challenges might we face? In a new paper (arxiv.org/abs/2310.13018 ), we describe a framework that attempts to unify ideas from cognitive science, neuroscience and AI to address these questions. 1/2

Getting aligned on representational alignment

Biological and artificial information processing systems form representations that they can use to categorize, reason, plan, navigate, and make decisions. How can we measure the extent to which...

This paper is very much a work in progress, so feedback welcome! And thanks to all the contributors, and particularly first authors Ilia & Lukas for their hard work! 2/2