How VISReg Overcomes JEPA’s Representation Collapse – LeCun’s Endorsement

VISReg introduces separate scale and shape regularizations based on sliced Wasserstein distance to prevent representation collapse in JEPA world models, achieving state‑of‑the‑art results on 15 benchmarks without heuristic tricks and matching DINOv2 performance with only one‑tenth of the data.

Computer VisionJEPASelf-supervised Learning

0 likes · 16 min read

How VISReg Overcomes JEPA’s Representation Collapse – LeCun’s Endorsement

Machine Heart

Jul 14, 2026 · Artificial Intelligence

Why VISReg Excels: Solving Representation Collapse in JEPA Models

VISReg decouples regularization into independent scale and shape objectives using sliced Wasserstein distance, avoids gradient collapse, achieves state‑of‑the‑art results on 15 vision datasets with only about one‑tenth of the data, and offers linear computational complexity and strong OOD generalization.

JEPASelf-supervised LearningVISReg

0 likes · 15 min read