arXiv:2609.06102v2 Announce Type: cross Abstract: Cellular automata is a local computation paradigm where complex behavior can arise from local interactions between simple functions. This paradigm ha...
arXiv:2608.30692v1 Announce Type: new Abstract: Video world models are increasingly used as simulators, yet visual fidelity alone does not show that a model maintains the hidden state of the world. W...
arXiv:2607. 27320v1 Announce Type: cross Abstract: Field-level inference of cosmological initial conditions from galaxy surveys requires a forward model that is simultaneously accurate in the non-linear regime, computationally efficient, and fully differentiable.
The paper introduces a sparse, residual world model that focuses on predicting only the changes in a scene by using a per-object change gate and a residual delta head. On a MuJoCo tabletop pushing benchmark, this approach outperforms a dense multilayer perceptron, achieving 2.5 to 4.6 times better next‑state pose accuracy with 8.6 to 11.1 times fewer parameters, maintaining high change‑detection F1 scores, and showing strong transfer across object counts. In autoregressive rollout and sampling‑based planning, the sparse model accumulates less error and enables successful planning where dense models fail.
arXiv:2603. 16689v2 Announce Type: replace Abstract: Next-token predictors often appear to develop internal representations of the latent world and its rules.
The paper investigates how transformers can possess a world model despite exhibiting behavioral failures. Using TaxiGPT, a transformer trained on random Manhattan walks, the authors show that the model internally represents intersections, streets, and its position, and uses a goal compass for navigation. They attribute failures to interference between overlapping intersection features and demonstrate that affordance packing mitigates these errors, concluding that world‑modeling abilities emerge at distinct training stages and should be studied mechanistically rather than merely observed behaviorally.
arXiv:2602. 23164v2 Announce Type: replace Abstract: Foundation models must handle multiple generative processes, yet mechanistic interpretability largely studies capabilities in isolation; it remains unclear how a single transformer organizes multiple, potentially conflicting "world models".
arXiv:2608.23526v1 Announce Type: new Abstract: World models can predict video without learning dynamics that they reliably preserve. We test whether a frozen DreamerV3 trained only on pendulum video...
arXiv:2608. 14530v1 Announce Type: cross Abstract: Interactive game world models typically autoregress visual observations directly in pixel or latent space, forcing structured properties such as pose, geometry, and occlusion to be implicitly maintained by the same generative sequence.
arXiv:2608. 01049v1 Announce Type: cross Abstract: World models have attracted significant attention for their ability to capture and predict the structure and dynamics of the physical world.
arXiv:2609.10464v1 Announce Type: cross Abstract: Joint-Embedding Predictive Architecture (JEPA) world models learn a compact latent representation of the world that supports prediction and planning,...
arXiv:2608. 15958v1 Announce Type: new Abstract: Deciding whether a Sokoban puzzle is solvable is PSPACE-complete (Culberson, 1997): solutions can be exponentially long and there is no short certificate to check.