

Genie 3: A New Frontier for World Models with Jack Parker-Holder and Shlomi Fruchter - #743
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Episode Description
Today, we're joined by Jack Parker-Holder and Shlomi Fruchter, researchers at Google DeepMind, to discuss the recent release of Genie 3, a model capable of generating “playable” virtual worlds. We dig into the evolution of the Genie project and review the current model’s scaled-up capabilities, including creating real-time, interactive, and high-resolution environments. Jack and Shlomi share their perspectives on what defines a world model, the model's architecture, and key technical challenges and breakthroughs, including Genie 3’s visual memory and ability to handle “promptable world events.” Jack, Shlomi, and Sam share their favorite Genie 3 demos, and discuss its potential as a dynamic training environment for embodied AI agents. Finally, we will explore future directions for Genie research. The complete show notes for this episode can be found at https://twimlai.com/go/743.
Processing in Progress
This episode is being processed. The AI summary will be available soon. Currently transcribing audio...
Related Episodes

Why Vision Language Models Ignore What They See with Munawar Hayat - #758
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
57m

Scaling Agentic Inference Across Heterogeneous Compute with Zain Asgar - #757
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
48m

Proactive Agents for the Web with Devi Parikh - #756
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
56m

AI Orchestration for Smart Cities and the Enterprise with Robin Braun and Luke Norris - #755
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
54m

Building an AI Mathematician with Carina Hong - #754
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
55m

High-Efficiency Diffusion Models for On-Device Image Generation and Editing with Hung Bui - #753
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
52m
No comments yet
Be the first to comment