Neural Fields as World Models

ArXi:2602.18690v2 Announce Type: replace-cross Humans rehearse possible futures offline, as in mental practice and perhaps dreaming, suggesting that world models may task learning away from the environment. Standard machine learning world models compress visual input into latent vectors, discarding the spatial structure that characterizes sensory cortex. We propose isomorphic world models: architectures that preserve sensory topology, so physics prediction becomes geometric propagation rather than abstract state transition.