NextWM: Non-Extensive Joint Embedding Predictive Architectures

World models that plan in a learned latent space rely on a distributional regularizer to prevent representation collapse, and the target of that regularizer shapes the geometry in which the planner measures progress toward a goal. Current latent prediction world models fix this target to a Gaussian distribution $\mathcal{N}(0,1)$. We ask what happens when that choice is relaxed. NextWM (Non-extensive World Model) replaces the Gaussian with a heavy-tailed $q$-Gaussian from Tsallis statistics, which recovers the Gaussian as a special case, while keeping the architecture, prediction loss, characteristic-function estimator and planner unchanged. Across four manipulation and navigation environments, NextWM predicts future latents more accurately than a trained world model with the Gaussian target on every task, yet its planning success still need further investigation. Our results shows the potential benefits of non-extensive targets for latent prediction world models, and motivates future work on how the geometry of the latent space affects planning.