Login / Signup

4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities.

Roman BachmannOguzhan Fatih KarDavid MizrahiAli GarjaniMingfei GaoDavid GriffithsJiaming HuAfshin DehghanAmir Zamir
Published in: CoRR (2024)
Keyphrases