arXiv:2607. 02403v1 Announce Type: cross Abstract: Decision-time planning with action-conditioned world models has become a popular paradigm for embodied control.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2608. 06994v1 Announce Type: cross Abstract: World Action Models (WAMs) aim to construct a unified architecture capable of understanding world state evolution and guiding to generative motion planning.
arXiv:2604. 03208v2 Announce Type: replace Abstract: World models are a promising path to zero-shot embodied control through planning.
arXiv:2606. 08775v1 Announce Type: cross Abstract: Visual world models have shown great potential in learning complex system dynamics.
arXiv:2608. 07746v1 Announce Type: new Abstract: Long-horizon humanoid loco-manipulation requires composing versatile whole-body skills and reliable high-level decision making.
arXiv:2604. 26182v2 Announce Type: replace-cross Abstract: World models of embodied agents predict future observations conditioned on an action taken by the agent.
arXiv:2608. 09298v1 Announce Type: cross Abstract: Action-conditioned world models (ACWMs) promise to provide embodied AI with scalable predictive simulators for planning, policy evaluation, and data generation.