D-JEPA: A Decision-Aligned Latent World Model

2026-09-21

AI Summary

本文针对预测准确但决策不佳的问题，提出D-JEPA模型，通过学习执行结果中的决策相关关系来优化未来候选方案的选择。

Abstract

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.

Problem

• latent world model
• decision-local prediction gap
• candidate futures

Innovation

• Decision-Aligned
• Latent World Model
• Permutation-Equivariant Operator
• Predictive Geometry
• JEPA-Compatible