D-JEPA: A Decision-Aligned Latent World Model
On the map: World models → Latent predictive world models also fits: Embodied and robot world models
Abstract (arXiv)
Latent world models predict the consequences of actions, but accurate prediction does not guarantee that latent distance reflects which candidate will execute successfully. We identify a decision-local prediction gap: among the few futures competing for execution, a candidate predicted closer to the goal can produce a worse realized outcome than an available alternative. We introduce D-JEPA, a decision-aligned latent world model that learns decision-relevant relations among candidate futures from executed outcomes. A bounded, permutation-equivariant operator jointly reasons over goal-relative predictive features and ordinal evidence, refining pretrained predictive geometry where action choices are most consequential. Restricted predictor adaptation and a shared ordinal interface extend this alignment across complementary predictive geometries. D-JEPA further realizes the learned decision structure in JEPA-compatible future representations, enabling deployment through native latent-distance planning. Evaluations across latent control, manipulation, pretrained action-producing models, physical robots and autonomous driving demonstrate improved action selection, including 87.89% success on PushT, a 15.04-point average gain on RoboTwin, and a 17-point gain on physical robot tasks. These results establish decision-relevant relational structure as a direct bridge between predictive world modeling and effective control.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Latent predictive world models, one of 11 directions in World models. Builds on 15 of its 17 references that are in the map. First posted on arXiv 21 Sep 2026.
Builds on
15 of 17 references.
Closest ancestors · 8
Same direction, newest first
- 2026Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control28 Jul
- 2026A Control Theory of Predictability in Latent World Models11 Jul
- 2026Fast LeWorldModel24 Jun
- 2026LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels13 Mar
- 2025What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?30 Dec
- 2024DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning7 Nov
- 2023Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture19 Jan
- 2018Learning Latent Dynamics for Planning from Pixels12 Nov
Other references · 7
- 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
- 2018DeepMind Control Suitecited by 956
- 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 809
- 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 512
- 2025Non-conflicting Energy Minimization in Reinforcement Learning based Robot Controlcited by 5
- 2026Var-JEPA: A Variational Formulation of the Joint-Embedding Predictive Architecture - Bridging Predictive and Generative Self-Supervised Learningcited by 4
- 2026Variational Neural Belief Parameterizations for Robust Dexterous Grasping under Multimodal Uncertaintycited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Toward Physically Grounded JEPA World Models for Goal-Conditioned Robotic Planning
- 2026Is Forward Prediction Enough? Physical State Grounding for JEPA World Models
- 2026The Planning Limits of Latent World Models
- 2026Predicting Consequences and Reinforcing Navigation Policies with Latent World Models
- 2026Action-Consequence Alignment for Reliable Planning and Self-Improving in Latent World Models
- 2026Decision-Metric Alignment in Latent World Models: Diagnostics and Action-Conditioned Objectives for MPC Planning
- 2026Towards Predictive, Aligned, and Scalable Robot Learning
- 2026Modeling Latent Disturbances for Robust Decision-Making in World Models