metaai·lightalo unofficial · independent
Universe / World Models & Embodied AI / I-JEPA
World Models & Embodied AI · 2023

I-JEPA

LeCun's world-model bet, realized: predict representations, not pixels

open source superseded ViT-H/14 632M params

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

Try it yourself

Lineage

Led toV-JEPA

See the whole family tree →

Sources

More in World Models & Embodied AI

Ego-Exo4DPARTNROpenEQAMeta MotivoV-JEPA 2Ego4D

Read the World Models & Embodied AI story on the sky →

✦ Open on the map Explore World Models & Embodied AI Quiz me