Description
Chair: Uros Seljak
How could machines learn as efficiently as humans and animals?
How could machines learn how the world works and acquire common sense?
How could machines learn to reason and plan?
Current AI architectures, such as Auto-Regressive Large Language
Models fall short. I will propose a modular cognitive architecture
that may constitute a path towards answering these questions. The
centerpiece of the architecture is a predictive world model that
allows the system to predict the consequences of its actions and to
plan a sequence of actions that optimize a set of objectives. The
world model employs a Hierarchical Joint Embedding Predictive
Architecture (H-JEPA) trained with self-supervised learning.
The JEPA learns abstract representations of the percepts that are
simultaneously maximally informative and maximally predictable.
The corresponding working paper is available here:
https://openreview.net/forum?id=BZ5a1r-kVsf
