Flow-JEPA: Robust Latent Dynamics for JEPA World Models via Flow Matching
cs.LG, cs.AI
Submitted: 2026-08-29
Updated: 2026-09-26
Code: https://github.com/HuoYanchen/Flow-JEPA
Terminology
Sources
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
- Revisiting Feature Prediction for Learning Visual Representations from Video
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- World Models
- Dream to Control: Learning Behaviors by Latent Imagination
- Mastering Atari with Discrete World Models
- Mastering Diverse Domains through World Models
- Training Agents Inside of Scalable World Models
- Temporal Difference Learning for Model Predictive Control
- VJEPA: Variational Joint Embedding Predictive Architectures as Probabilistic World Models
- Action-to-Action Flow Matching
- Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching
- Flow Matching for Generative Modeling
- Rectified Flow: A Marginal Preserving Approach to Optimal Transport
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- Transformers are Sample-Efficient World Models
- Flow Matching in Feature Space for Stochastic World Modeling
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks