Ask what should change when the equation is manipulated, then let the visualization test that expectation.
Foundation Lab
Video World Models
Merges generative modeling with dynamics modeling
#97VideoWMGenerative Models
key equation
p_\theta(x_{1:T}|c) = \prod_t p_\theta(x_t | x_{<t}, c)Selected Foundation Object
Keep the equation fixed; move through the evidence.
Concept 97 of 100VideoWMGenerative Models / Phase 13: Cutting-edge 2024-2025 research
Current question
Not just "video generation" but learned physics engine
p_\theta(x_{1:T}|c) = \prod_t p_\theta(x_t | x_{<t}, c)Use the runnable panel, the key equation, and canonical papers as separate forms of evidence for the same object.
The useful learning product is the reusable mechanism you can carry into another model, paper, or engineering tradeoff.
Use prerequisites, dependents, and semantic links to repair the next gap without leaving the object behind.
Why It Matters for Modern Models
- Merges generative modeling with dynamics modeling
- Precursor to general planning/agents
- Sora shows emergence of 3D consistency, object permanence
What Tutorials Skip
What is still poorly explained in textbooks and papers:
- Not just "video generation" but learned physics engine
- Emergent properties: camera control, object tracking, causality
- Can imagine "what happens if" for planning
Interactive Visualization
Core Math (Optional Deep Dive)
If you want intuition first, start with the key equation and the visualization. Come back here for the full walkthrough.
Key Equation
Video as learned dynamics. Autoregressive:
Diffusion over latent :
Video generators = learned simulators of physical world.