Video yükleniyor...
Video Yüklenemedi
We are releasing 4M-21 with a permissive license, including its source code and trained models. It's a pretty effective multimodal model that solves 10s of tasks & modalities. See the demo code, sample results, and the tokenizers of diverse modalities on the website. IMO, the multitask learning aspect of... show more
69,241 görüntüleme • 2 yıl önce •via X (Twitter)
6 Yorum

Amir Zamir2 yıl önce
shoutout to @roman__bachmann, @oguzhanthefatih, @dmizrahi_ who led the work, along with @aligarjani, @mingfei_gao, David Griffiths, @hujm99, @afshin_dn, @zamir_ar.

Shikun Liu2 yıl önce
Great work! And thanks for open-sourcing to the community. :)

Isaac Kargar2 yıl önce
No audio input?

Amir Zamir2 yıl önce
It’s a matter of data. Otherwise IMO the method will work as-is.

Lele2 yıl önce
massive

Puneet (Linkedin Top Voice | AI and Data speaker)2 yıl önce
@zamir_ar You guys are nailing it! #multimodal #framework



