Yann LeCun notes that I-JEPA does not require knowledge that the input is an image, unlike DINO, which needs image-specific transformations.
It doesn't need to know that it's an image, for example, because the only thing it needs to know is how to do this masking. Whereas with DINO, you need to know it's an image because you need to do things like geometry transformation and blurring and things like that that are really image specific.