arXiv:2605. 08732v2 Announce Type: replace-cross Abstract: Modern vision-based world models can represent observations as compact yet expressive latent manifolds, but fast goal-oriented planning in these spaces remains challenging.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.
arXiv:2604. 03208v2 Announce Type: replace Abstract: World models are a promising path to zero-shot embodied control through planning.
arXiv:2607. 17973v1 Announce Type: new Abstract: Latent world models have emerged as a powerful planning paradigm by learning action-conditioned predictive dynamics and using them as internal simulators to imagine and evaluate candidate action sequences.
arXiv:2608. 16287v1 Announce Type: new Abstract: Joint-embedding predictive world models plan by scoring predicted terminal embeddings against a goal embedding using a cost defined on the representation itself.
arXiv:2607. 12547v1 Announce Type: cross Abstract: We investigate whether temporal hierarchy can improve LeWorldModel on long-horizon goal-conditioned control.
arXiv:2608. 14125v1 Announce Type: new Abstract: LeWM is a lightweight visual world model that learns latent dynamics end-to-end from pixels and ranks candidate action sequences by the distance between their predicted endpoints and the goal.
arXiv:2606. 07974v1 Announce Type: cross Abstract: A learned world model provides a powerful physical intuition for evaluating future states.