aiqbench analysis
FF-JEPA addresses critical scalability issues in Joint Embedding Predictive Architectures by introducing a hierarchical, action-free latent planner that eliminates the dependency on explicit goal images. This approach decomposes complex trajectories into manageable subgoals, effectively preventing long-horizon collapse in world models without incurring the high computational costs of traditional optimization methods. Preliminary results on the PushT benchmark suggest this framework offers a viable path toward practical, goal-free planning for real-world robotic tasks.
FF-JEPA: Long-Horizon Planning in World Models with Latent Planners
arXiv:2606.09311v1 Announce Type: new Abstract: Joint Embedding Predictive Architectures (JEPAs) have shown promising world modeling capabilities, enabling planning in latent space by optimizing action trajectories using methods like the Cross-Entropy Method (CEM). These methods are, however, too computationally expensive and ineffective for long-horizon planning. Furthermore, these methods typically require an explicit image of the goal state, which is not always possible in real-world tasks. In this work, we tackle these limitations by proposing Forward-Forward-JEPA (FF-JEPA), a hierarchical approach leveraging two forward dynamics models. Alongside a standard action-conditioned forward model, we introduce an action-free latent planner that predicts the next subgoal given the current state. This approach removes the need for goal images and enables long-horizon planning by decomposing complex trajectories into a sequence of tractable, short-term optimization problems. Preliminary results on PushT demonstrate that FF-JEPA successfully overcomes flat world models' long-horizon collapse, highlighting this approach as a promising direction for goal-free planning.
Abstract:Joint Embedding Predictive Architectures (JEPAs) have shown promising world modeling capabilities, enabling planning in latent space by optimizing action trajectories using methods like the Cross-Entropy Method (CEM). These methods are, however, too computationally expensive and ineffective for long-horizon planning. Furthermore, these methods typically require an explicit image of the goal state, which is not always possible in real-world tasks. In this work, we tackle these limitations by proposing Forward-Forward-JEPA (FF-JEPA), a hierarchical approach leveraging two forward dynamics models. Alongside a standard action-conditioned forward model, we introduce an action-free latent planner that predicts the next subgoal given the current state. This approach removes the need for goal images and enables long-horizon planning by decomposing complex trajectories into a sequence of tractable, short-term optimization problems. Preliminary results on PushT demonstrate that FF-JEPA successfully overcomes flat world models' long-horizon collapse, highlighting this approach as a promising direction for goal-free planning.
Artificial Intelligence (cs.AI)
arXiv:2606.09311 [cs.AI]
(or arXiv:2606.09311v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.09311 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 241 words
Related coverage
World Models and Yann LeCun’s Bet Against Large Language Models
Quantum Zeitgeist · Jul 17, 2026
H-JEPA: End-to-End Learning of Hierarchical World Models for Visual Planning
arXiv · Oct 6, 2026
Latent Goal Prediction from Language for Model-Based Planning
arXiv · Oct 6, 2026
[AINews] Fal’s H3 Max Live breaks the infinite videogen barrier
Latent Space · Sep 1, 2026