DiffusionGemma Technical Report

Just wanted to share this, I found it was a really nice resource to understand how diffusion Gemma worked: https://newsletter.maartengrootendorst.com/p/a-visual-guide-...

The really interesting thing to me was that they didn’t need to train this model from scratch they just used their existing MOE checkpoint:

“To convert a decoder-only model (Gemma 4 26B A4B) into a denoiser, we can make use of something it is not directly using when generating tokens, namely the logits of all tokens!”

What makes me hopeful about this release is that possibly this same conversion can be applied to other open models and we might see a bunch of diffusion versions of existing local models. It’s exciting stuff!

Appealing results... do we think there is scope to close the accuracy gap against AR models? or even leverage the "Bidirectional Reasoning and Self-Correction" into an overall advantage?

I'm very interested in Diffusion text models. The concept of taking noise and adding words starting randomly all over the response, and filling in the noise from there on breaks my brain.

I'm sure I have a fundamental misunderstanding of the technology, though.

there's still JEPA to be integrated before AGI.

Would DiffusionGemma be suitable candidate for DFlash 2?