observation · 7 Mar 2024 · 38:09

Yann LeCun explains that I-JEPA involves masking parts of an image and training the system to predict the representation of the uncorrupted image.

in the case of I-JEPA, you don't need to do any of this, you just mask some parts of it, right? You just basically remove some regions like a big block, essentially.

Watch at 38:09