Introducing Meta Perception Encoder: a vision encoder setting new standards in image & video tasks. It excels in zero-shot classification & retrieval, surpassing existing models. Learn more about Meta Perception Encoder, read the research paper, and download the code and dataset

Help to excelsheet❓

Decode the labor market! Learn how to track jobless claims using FRED and Python in my latest free Substack post. 📈 A must-read for data enthusiasts & economists. Dive into how data insights can shape your understanding of the economy.

"A vision encoder setting new standards in image & video tasks, excelling in zero-shot classification & retrieval."

just impressive how Siglip stills so close with less than 1/6 of the parameters @giffmana

It’s over bro, rest.

Its ability to excel in zero-shot tasks pushes the boundaries of image and video processing. Can’t wait to dive into the research and see how it outperforms current models.

@AIatMeta, this could be a game-changer in visual technology. excited to see its impact.

Ok...? What is it?

Interesting 👀

42 Homies 😒

Incredible progress here. Meta Perception Encoder shows what's possible when you unify architecture across image and video tasks. Zero-shot performance is no longer optional... it's the new baseline. Excited to see how this accelerates real-world applications. Always looking to the future!