|
|
|
|
|
|
by santiagobasulto
13 days ago
|
|
|
Not at all, I had the same feeling as yours the first time I read it. I think the key is that the "encoder" they're using is just a linear projection, which is probably pretty fast and memory efficient. A single matmul vs a ViT encoder is probably a huge win. |
|
|