Vision tokens are a good compression medium because with one vision token you have one vector of N elements, but with textual tokens you have M vectors of N elements, because one vision token represent multiple pixels (and possibly multiple words). This is why its a good compression medium for compute.
It will never be as precise as textual tokens but it can be really good as they show in the paper.
It will never be as precise as textual tokens but it can be really good as they show in the paper.