Lots of confusion about what a world model is. Here is my definition:

Given:
- an observation x(t)
- a previous estimate of the state of the world s(t)
- an action proposal a(t)
- a latent variable proposal z(t)

A world model computes:
- representation: h(t) = Enc(x(t))
-

Yann LeCun How would you say this is similar and/or different than Active Inference?

Active Inference Institute Finding the best sequence of actions that minimize an objective function (an energy) measured over the predicted trajectory is very much like inferring latent variables.
If you insist on being Bayesian, then you infer a distribution over action sequences by trading the average