UpNext AI Deep Dive: World Models, Spatial Intelligence, and the Race to Teach AI Reality

About this episode

In this deep-dive episode of UpNext AI, we explore the growing debate around world models — AI systems designed to predict and reason about how the world changes over time. Large language models made AI useful as a software and knowledge interface, but researchers like Yann LeCun and Fei-Fei Li argue that acting in the physical world requires something more: spatial understanding, prediction, planning, and a model of consequences.

We break down why world models are attracting major investment, how they differ from traditional robotics, why video models changed the conversation, and what recent research papers suggest about the path from passive observation to real-world action. We also look at the risks: unclear architectures, expensive data, reliability gaps, and the challenge of turning compelling research into durable businesses.

Sources and further reading

Interviews

Fei-Fei Li interview:
 https://youtu.be/wDeXfFQcJxk?si=9oxB3NWXZiqeuj1K

Yann LeCun interview:
 https://youtu.be/_PioN-CpOP0?si=K7RRD7BtfKpQ9cCI

Company and funding context

Reuters — Fei-Fei Li’s World Labs raises $1 billion in funding:
 https://www.reuters.com/business/ai-pioneer-fei-fei-lis-world-labs-raises-1-billion-funding-2026-02-18/

World Labs — funding announcement:
 https://www.worldlabs.ai/blog/funding-2026

TechCrunch — Yann LeCun’s AMI Labs raises $1.03 billion to build world models:
 https://techcrunch.com/2026/03/09/yann-lecuns-ami-labs-raises-1-03-billion-to-build-world-models/

Research papers

V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning:
 https://arxiv.org/abs/2506.09985

Humanoid World Models: Open World Foundation Models for Humanoid Robotics:
 https://arxiv.org/abs/2506.01182

GenCast: Probabilistic Weather Forecasting with Machine Learning:
 https://www.nature.com/articles/s41586-024-08252-9

WorldSimBench / Towards Video Generation Models as World Simulators:
 https://openreview.net/forum?id=ejGAytoWoe

Video models and robotics context

OpenAI — Video generation models as world simulators:
 https://openai.com/index/video-generation-models-as-world-simulators/

OpenAI — Sora: Creating video from text:
 https://openai.com/index/sora/

Boston Dynamics — Large Behavior Models and Atlas Find New Footing:
 https://bostondynamics.com/blog/large-behavior-models-atlas-find-new-footing/

Toyota Research Institute — AI-Powered Robot by Boston Dynamics and TRI takes key step toward general-purpose humanoids:
 https://www.tri.global/news/ai-powered-robot-boston-dynamics-and-toyota-research-institute-takes-key-step-towards-general

IEEE Spectrum — Boston Dynamics Atlas Learns From Large Behavior Models:
 https://spectrum.ieee.org/boston-dynamics-atlas-scott-kuindersma
Audio generation: ElevenLabs https://www.upnext.fm/eleven