I-JEPA
LeCun's world-model bet, realized: predict representations, not pixels
Latest: I-JEPA (Jun 2023, CVPR 2023)
The first realized piece of Yann LeCun's world-model vision (June 2023): an Image Joint-Embedding Predictive Architecture that learns by predicting abstract representations of masked image regions rather than pixels, delivering strong semantic features with far less compute than pixel-reconstruction or contrastive methods.
Why it matters
I-JEPA was the first working piece of LeCun's world-model program: learn by predicting abstract representations of masked regions rather than pixels. It reached strong semantic features while training a 632M ViT-Huge in under 72 hours on 16 A100s — an order of magnitude cheaper than pixel-reconstruction methods — and launched the JEPA family.
Facts
- Trained a 632M-parameter ViT-Huge in under 72 hours on 16 A100s — an order of magnitude cheaper than comparable pixel-space methods at the time.
Try it yourself
ijepa_vith14_1k on Hugging Face ↗ Code on GitHub ↗ Read the paper ↗