Fitting Vision Adapters at Frontier Scales
Training a small projector between a frozen vision encoder and language model is an established approach to multimodal learning. As the parameter count of language models scales dramatically, we revisit which vision capabilities this approach can add while keeping their pretrained weights fixed. Here we train a 50M par...
Jaehoon Lee, Harry B. Partridge, M. Jayasekara et al.
· 0 citations