Picture for David Mizrahi

David Mizrahi

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

Add code
Jun 14, 2024
Viaarxiv icon

4M: Massively Multimodal Masked Modeling

Add code
Dec 11, 2023
Viaarxiv icon

MultiMAE: Multi-modal Multi-task Masked Autoencoders

Add code
Apr 04, 2022
Figure 1 for MultiMAE: Multi-modal Multi-task Masked Autoencoders
Figure 2 for MultiMAE: Multi-modal Multi-task Masked Autoencoders
Figure 3 for MultiMAE: Multi-modal Multi-task Masked Autoencoders
Figure 4 for MultiMAE: Multi-modal Multi-task Masked Autoencoders
Viaarxiv icon