AI World Models

A comprehensive course for technically curious learners who want to understand how AI systems learn internal representations, imagine futures, plan actions, generate interactive worlds, and support physical AI.

4 sections ยท 16 lessons

Course outline

Modeling Foundations

  1. Mental Simulators
  2. Latent State Compression
  3. Action-Conditioned Dynamics
  4. Planning by Imagination
  5. Audit a World-Model Claim

Control Algorithms

  1. Model-Based Control
  2. MuZero's Planning Targets
  3. DreamerV3's Generality
  4. Bad Dreams and Uncertainty
  5. Choose the Control Loop

Video World Models

  1. Visual Patch Scaling
  2. Coherence and State
  3. Genie's Latent Actions
  4. V-JEPA's Embedding Predictions
  5. Judge a Video Simulator

Physical AI

  1. World Foundation Models
  2. Digital Twins and Synthetic Data
  3. Benchmarks for Causality
  4. Roadmap and Limits
  5. Build a World-Model Scorecard

Start learning with Wondering