> you will need a very domain-specific use for this to be useful imo
The main premise of this idea is how general and widely applicable it is. They also show examples of how it works on images.
A common tokenizing paradigm would be a huge step towards consolidating how different modalities are preprocessed - something I believe is quite useful for intelligence to scale well across modalities.
The main premise of this idea is how general and widely applicable it is. They also show examples of how it works on images.
A common tokenizing paradigm would be a huge step towards consolidating how different modalities are preprocessed - something I believe is quite useful for intelligence to scale well across modalities.