Converting pixels or visual information into vector sequences is conceptually similar to treating sequences as 'language' in the abstract sense—both are sequential representations—and the distinction between sequential and parallel generation (as in diffusion models) is largely immaterial conceptually, though it may provide practical efficiency gains of around 10x.
factualpending
Speaker
Ilya SutskeverEvidence Quote
“I would argue that on some level this distinction is immaterial. I claim that on some level it doesn't really matter. It matters as in like you can get a 10x efficiency gain, which is huge in practice, but conceptually I claim it doesn't matter.”
Created: 8/10/2026, 10:48:45 PM
Your notes
Loading notes...