We consider the problem of variational Bayesian inference in a latent variable model where a (possibly complex) observed stochastic process is governed by the solution of a latent stochastic differential equation (SDE).

In-context learning (ICL) is one of the most powerful and most unexpected capabilities to emerge in recent transformer-based large language models (LLMs).

This makes the world model softly state-invariant.

Inference in the introduced linear Gaussian SSM is straightforward and can be performed using Kalman prediction and observation updates.

Understanding how the collective activity of neural populations relates to computation and ultimately behavior is a key goal in neuroscience.