As pointed out by Jesus Rodriguez on TheSequence, "With all the hype surrounding generative AI, we sometimes overlook the thrilling advancements in other areas of the deep learning ecosystem." I-JEPA from Meta research is one such.
Meta, a company I generally detest, is making real contributions in AI, including significant (partly) open source efforts such as the LLAMA model, which has fueled massive independent development. I trust Meta … to do what’s good for Meta alone, but in AI they’re (probably accidentally) doing a lot of good.