#long-tail-concepts

[ follow ]
fromHackernoon
1 year ago

What 34 Vision-Language Models Reveal About Multimodal Generalization | HackerNoon

We delved into the five pretraining datasets of 34 multimodal vision-language models, analyzing the distribution and composition of concepts within, generating over 300GB of data artifacts that we publicly release.
Artificial intelligence
[ Load more ]