No AI summary available for this article.
Why It Matters
Latent world models predict future states for goal-directed planning using action chunks spanning multiple primitive steps.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Latent world models predict future states for goal-directed planning using action chunks spanning multiple primitive steps. Existing methods typically use fixed-length chunks and either omit goal-conditioned action generation or limit their supervision to short goal spans. We introduce FlexiWorld, a JEPA-based world model that combines mixed-span goal supervision with variable-length action chunks to improve long-horizon control. During training, we sample varying goal spans and randomly partition the actions into variable-length chunks. We jointly train the world model with a causal action en...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.35138v1 · Indexed 44 minutes ago