FF-JEPA introduces a two-model hierarchical structure with an action-free latent planner to decompose long-horizon planning into short subgoals in latent world models.
Grounding generated videos in feasible plans via world models.arXiv preprint arXiv:2602.01960
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
ExoActor uses exocentric video generation to implicitly model robot-environment-object interactions and converts the resulting videos into task-conditioned humanoid control sequences.
citing papers explorer
-
FF-JEPA: Long-Horizon Planning in World Models with Latent Planners
FF-JEPA introduces a two-model hierarchical structure with an action-free latent planner to decompose long-horizon planning into short subgoals in latent world models.
-
ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control
ExoActor uses exocentric video generation to implicitly model robot-environment-object interactions and converts the resulting videos into task-conditioned humanoid control sequences.