Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> so they can't be integrated

That's overly pessimistic. Diffusion models take an input and produce an output. It's perfectly possible to auto-regressively analyze everything up to the image, use that context to produce a diffusion image, and incorporate the image into subsequent auto-regressive shenanigans. You'll preserve all the conditional probability factorizations the LLM needs while dropping a diffusion model in the middle.



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: