---

TALK: “Open-Endedness and World Models”

Abstract
The pursuit of Artificial Superintelligence (ASI) requires a shift from narrow objective optimization towards embracing Open-Endedness—a research paradigm, pioneered in AI by Stanley, Lehman and Clune, that is focused on systems that generate endless sequences of novel but learnable artifacts. In this talk, I will present our work on large-scale foundation world models that can generate a wide variety of diverse environments, and in turn be used to train more general and robust agents.

---

Short Bio

I am a Director, Principal Scientist, and the Open-Endedness Team Lead at Google DeepMind.
I am also a Professor of Artificial Intelligence at the Centre for Artificial Intelligence in the Department of Computer Science at University College London (UCL) where I am PI of the UCL Deciding, Acting, and Reasoning with Knowledge (DARK) Lab, and a Fellow of the European Laboratory for Learning and Intelligent Systems (ELLIS).

My work focuses on Artificial General Intelligence, Open-Endedness, and Self-Improvement, and it has received two Best Paper Awards at ICML in 2024 and a Keynote at ICLR in 2025.