MotionJEPA: Preventing Temporal Feature Collapse by Capturing Visual Changes in Latent Space

arXiv:2609.23881 · cs.CV · Submitted 2026-09-20 · Read on arXiv

cs.CV

Submitted: 2026-09-20

Updated: 2026-09-20

Code: https://github.com/mkarmann/motion-jepa

Terminology

• Embeddings — 26× in this paper · explained in 2 episodes
• World Model — 17× in this paper · explained in 7 episodes
• Regularization — 14× in this paper · explained in 3 episodes
• Linear probe — 11× in this paper · explained in 2 episodes
• Latent Representation — 9× in this paper · explained in 2 episodes
• Latent Space — 6× in this paper · explained in 7 episodes
• Self-Supervised Learning — 6× in this paper · explained in 8 episodes
• Angular Error — 5× in this paper · explained in 1 episode
• Benchmark — 5× in this paper · explained in 2 episodes
• Latent Representations — 5× in this paper · explained in 3 episodes
• Robustness — 4× in this paper · explained in 5 episodes
• Core — 3× in this paper · explained in 2 episodes
• Latent World Models — 3× in this paper · explained in 2 episodes
• Downstream Tasks — 2× in this paper · explained in 2 episodes
• Representation Learning — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Ablation Studies — 1× in this paper · explained in 1 episode
• Action Decoder — 1× in this paper · explained in 1 episode
• Action-Conditioned Dynamics — 1× in this paper · explained in 1 episode
• Activation Function — 1× in this paper · explained in 1 episode
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Closed-Loop Control — 1× in this paper · explained in 3 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Covariate Shift — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Entanglement — 1× in this paper · explained in 4 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Model Predictive Control (MPC) — 1× in this paper · explained in 5 episodes
• Normalized Mean Squared Error — 1× in this paper
• Two-stage training — 1× in this paper · explained in 2 episodes
• Wasserstein Distance — 1× in this paper · explained in 4 episodes

Sources

• Learning Invariant Visual Representations for Planning with Joint-Embedding Predictive World Models
• DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
• Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning
• When Does LeJEPA Learn a World Model?

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models