Findling, C.; Lee, J. K.; Bakermans, J. J. W.; Pouget, A.; Wyart, V.

The Bayesian Brain hypothesis assumes that cognition relies on internal generative models of the world, yet existing implementations remain constrained by pre-specified, task-specific generative structures and computationally heavy iterative inference schemes. Here, we introduce modular neural state-space models as a scalable realization of the Bayesian Brain, replacing fixed generative structures and pre-specified inference rules with learned world-model components and amortized neural updates. This framework preserves the core commitment to explaining observations through hidden causes while making inference learned and reusable rather than pre-specified and task-specific. Our modular implementation of these models affords learned components to be seamlessly recombined and stacked across superficially different tasks that share similar latent dynamics. Such computational reuse supports zero-shot generalization and predicts selective correlations of inference parameters between tasks. We confirm these key predictions in human behavior, identifying learned and reusable world-model components as a candidate computational principle for flexible cognition.