Participants are not allowed to modify the training procedure.

While these advances use different algorithmic techniques, e.g., contrastive learning, diffusion, or auto-regressive modeling, they all rest on a common foundation: large datasets containing paired image-text examples.

Unless stated otherwise we use American English for transcriptions.

That which we call a rose by any other name would smell as sweet."

We show that any (possibly non-private) learning rule can be effectively transformed to a private learning rule with only a polynomial overhead in the mistake bound.

Recent studies have shown promising results on utilizing large pre-trained image-language models for video question answering.

Recently, there has been a marked increase in interest regarding the generalization capabilities of unregularized gradient-based learning methods.