Path Integration and Object-Location Binding Emerge in an Action-Conditioned Predictive Sequence Network

ArXi:2602.03490v2 Announce Type: replace Adaptive cognition requires structured internal models of objects and their relations. Predictive neural networks are often proposed to learn such world models, but how these are instantiated and how they prediction remain unclear. We investigate this in a minimal in-silico setting. A recurrent neural network samples tokens sequentially from 2D continuous token scenes and is trained to predict the upcoming token from the current input and a saccade-like displacement.