I don’t think they ‘consistently find’ anything, except about possibly CLIP (which we’ve known to have severe flaws ever since it came out, as expected from a contrastive loss, despite of course many extremely valuable uses). Unless I’m missing something in the transcript, Computerphile doesn’t mention this at all.
Key graph: https://arxiv.org/pdf/2404.04125#page=6
I don’t think they ‘consistently find’ anything, except about possibly CLIP (which we’ve known to have severe flaws ever since it came out, as expected from a contrastive loss, despite of course many extremely valuable uses). Unless I’m missing something in the transcript, Computerphile doesn’t mention this at all.