SkeLAM decomposes latent actions into skeleton-guided kinematic and residual components to improve controllable robot world modeling and motion transfer.
Recent world action models provide visual foresight and future prediction for robot manipulation, but lack explicit mechanisms for compositional skill reuse. Agentic robotics combines code-based planning and reasoning with reusable skills, but often lacks predictive grounding in …
FRED improves single-step future video representations in world action models through self-distillation and temporal conditioning, boosting robot policy performance on long-horizon and unseen tasks.
arXiv:2610.30320v1 Announce Type: cross Abstract: World Action Models (WAMs) have emerged as a promising approach to learning generalist robot policies using rich spatiotemporal priors from pre-trained video diffusion models. A recent line of WAMs improves inference efficiency by…
arXiv:2610.29168v1 Announce Type: cross Abstract: World action models (WAMs) are shown to substantially diverge under generalization performance based on their generative backbones. We investigate this gap through the representational geometry that WAMs inherit from their backbon…
arXiv:2610.29408v1 Announce Type: new Abstract: Interactive video world models predict how an environment evolves under user actions, but most existing systems assume one controlled agent and one task-specific action interface. We study multi-agent video world modeling, where one…
arXiv:2610.27914v1 Announce Type: new Abstract: Real-world observations are noisy and often contain excessive task-irrelevant information. Effective world modeling and planning need to abstract observations into world state representations while filtering out irrelevant informati…
