[abotsis]

I’m not sure I follow this. Isn’t an LLMs dimensionality measured by how many parameters the model supports? Ie 10s of billions in some cases? If I understand it correctly, then, the model is already evaluating things in lots of dimensions and reducing it down to 1, as you say in the case of text, 2 dimensions in image generation, 3 should be pretty straightforward.

[btbuildem]

I think they're referring to the dimensionality of the input / output space, not the intermediate internal representation.