The AI Update XIX - World Models

What are “World Models,” and why should we care? Could AI really understand reality? Scott and Jhave sit down to explore the rise of World Models - the "engines" of machine intuition -to discuss how quickly they are evolving and what their existence means for the future of humanity (and the robots living alongside us) References Agarwal, N. et al. (2025) Cosmos World Foundation Model Platform for Physical AI. https://arxiv.org/abs/2501.03575 ByteDance. (2025) Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds. https://arxiv.org/abs/2511.08892 DeepMind SIMA Team. (2025) SIMA 2: A Generalist Embodied Agent for Virtual Worlds. https://arxiv.org/abs/2512.04797 Deng, J. et al. (2009) ImageNet: A Large-Scale Hierarchical Image Database. https://ieeexplore.ieee.org/document/5206848 Fisher, C., Coover, R., & Julian. (2026) [Untitled AR Skiing Project]. [No public URL available for this in-development project] Li, F.-F. (2025) From Words to Worlds: Spatial Intelligence is AI's Next Frontier. https://drfeifei.substack.com/p/from-words-to-worlds-spatial-intelligence Mao, J. et al. (2025) Robot Learning from a Physical World Model https://arxiv.org/abs/2511.07416 PAN Team, MBZUAI. (2025) PAN: A World Model for General, Interactable, and Long-Horizon World Simulation. https://arxiv.org/abs/2511.09057 Powers, R. (2000) Plowing the Dark. https://en.wikipedia.org/wiki/Plowing_the_Dark