A Generalization Theory for JEPA-Based World Models

arXiv:2606.27014 · cs.LG · Submitted 2026-06-25 · Read on arXiv

cs.LG

Submitted: 2026-06-25

Updated: 2026-09-29

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• World Model — 4× in this paper · explained in 7 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Regret — 1× in this paper · explained in 3 episodes

Sources

• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control
• LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
• Gaussian Embeddings: How JEPAs Secretly Learn Your Data Density
• VL-JEPA: Joint Embedding Predictive Architecture for Vision-language
• Value-guided action planning with JEPA world models
• When Does LeJEPA Learn a World Model?
• UniJEPA: A Unified Joint-Embedding Predictive Architecture for Task-Agnostic Visual World Modeling
• LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
• FF-JEPA: Long-Horizon Planning in World Models with Latent Planners
• Causal-JEPA: Learning World Models through Object-Level Latent Masking
• DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks