This work studies action-conditioned predictors built on five frozen self-supervised visual backbones, finding that a world model guides action selection reliably only when the goal lies within, or slightly beyond, the trajectory it imagines during planning.
Abstract
World models offer a promising way to help robots understand how the physical world evolves and plan complex behaviours through imagination. Yet existing studies mainly demonstrate what these models can accomplish, leaving unclear when their predictions remain useful for planning and where they fail. We study this question using action-conditioned predictors built on five frozen self-supervised visual backbones: V-JEPA 2, V-JEPA 2.1, VideoMAEv2, VideoPrism, and DINOv2. We use frozen backbones to test representations intended to transfer across environments. We evaluate these models on diverse Meta-World manipulation tasks and real-robot interactions from BridgeData V2. We find that a world model guides action selection reliably only when the goal lies within, or slightly beyond, the trajectory it imagines during planning. With five-step rollouts, the length the predictor was trained on, the world model ranks actions reliably only for targets five to ten control steps ahead, whereas task goals lie 16 to 53 steps away. Neither an 81-fold larger predictor nor longer-rollout training extends this range; the encoder affects both range and closed-loop success, with V-JEPA 2.1 performing most consistently. More fundamentally, the limit persists under perfect prediction: using the real simulator, success falls from 92% to 41% as the target moves from five to twenty steps ahead of a five-step rollout. Planning therefore requires either longer imagined trajectories or closer subgoals. For distant goals, pure imagination succeeds in 23% of episodes, planning with feedback (MPC) raises success to 30%, imagining as far as the goal to 47%, and nearby expert subgoals to 76%. Used within its plannable range, a world model can also improve a vision-language-action (VLA) policy: choosing among eight actions the VLA proposes raises its success from 65% to 77% across 16 different tasks.
Align Once, Evaluate Everywhere (AoE), a camera-space inverse-dynamics model pretrained on large-scale robot data, is introduced, which provides this recovery interface for different future sources across tasks and environments and raises the execution success of generated futures from near zero to 47.0%.
Chen Zhao, Zi-Peng Ye, Yi-Han Lin et al.· 0 citations
This work introduces Anchored Planning, which retrieves a recorded segment whose start and end resemble the current and goal observations, then aims at an observation shortly after its start, and without additional training, planning toward observed targets outperforms the LeWM planner on every task in the authors' lon...
World-action models jointly learn robot policies and predict future observations, making the representation space an interface between control and prediction. We study the design of this space through controlled comparisons, finding that neither reconstruction fidelity nor pre-trained perceptual features alone ensure e...
Hao-Yi Jiang, Liu Liu, Xin-Jiang Wang et al.· arXiv.org· 6 citations
Latent world models have shown a remarkable ability to predict future states and to plan in the real world. In practice, however, we lack a principled way to estimate how their capabilities scale with model size, data, and compute, an open problem that slows progress in the field. In this work we present RoboJEPA, a wo...
Artem Zholus, Nicolas Beltran-Velez, Jian-Hao Yuan et al.· 0 citations
To the knowledge, RP1 is the first method to fully learn how to improve multi-step plans and can be trained independently of and attached to any pretrained latent world model.
Action-conditioned JEPA world models enable planning toward visually specified goals without reconstructing future pixels, yet latent prediction alone does not explicitly encourage the learned representations to retain information relevant to robotic control. We introduce an end-to-end JEPA world model that augments la...
Mu-Yuan Liu, Yue-Ning Huang, Zhe Liang et al.· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.