Model
Transfusion
A unified multimodal model architecture that jointly trains multimodal tasks through a shared latent space, representing a direction in unified multimodal model (UMM) research.
Timeline (last 90 days)
Oct 16
The core characteristic of unified multimodal models (UMMs) is that a single model simultaneously possesses multi-task capabilities such as visual understanding, text understanding, and image generation; representative works include Chameleon, Transfusion, Janus, and others.
Unverified50%