23 points | by DSemba 2 hours ago ago
3 comments
This is amazing and I think will probably end up being a pretty important development.
I was just reading this great breakdown of how diffusion Gemma works: https://newsletter.maartengrootendorst.com/p/a-visual-guide-...
In reference to the difficulties with applying this to autoregressive LLMs - I wonder if these type of hybrids might be a good candidate for this approach.
If their numbers are real and hold up at scale, every image model trained before this is now obsolete.
I don't have enough context to know if this is actually cool or not, but it seems like it!
This is amazing and I think will probably end up being a pretty important development.
I was just reading this great breakdown of how diffusion Gemma works: https://newsletter.maartengrootendorst.com/p/a-visual-guide-...
In reference to the difficulties with applying this to autoregressive LLMs - I wonder if these type of hybrids might be a good candidate for this approach.
If their numbers are real and hold up at scale, every image model trained before this is now obsolete.
I don't have enough context to know if this is actually cool or not, but it seems like it!