NHacker Next
  • new
  • past
  • show
  • ask
  • show
  • jobs
  • submit
DiffusionGemma Technical Report (arxiv.org)
kamranjon 22 minutes ago [-]
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!

jermaustin1 22 minutes ago [-]
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.

embedding-shape 7 minutes ago [-]
DiffusionGemma goes one step further even, and does this denoising over multiple "canvases" which lets it do reasoning and separate out a "final reply" canvas, looks something like this: https://gist.github.com/embedding-shapes/f4cb46bad704b6d0168...

Diffusion text models for me is the more interesting type of LLMs for local usage, as it really makes good use of single GPUs for single responses, rather than auto-regressive ones, and is a lot faster! Probably the fastest model I've been able to run so far, ending up doing ~670 tok/s (depending on the type of text) on a Pro 6000

keel-control 20 minutes ago [-]
there's still JEPA to be integrated before AGI.

Would DiffusionGemma be suitable candidate for DFlash 2?

discobot2 24 seconds ago [-]
its more of a competitive approach to improve compute utilisation at lower batch sizes
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact
Rendered at 14:32:47 GMT+0000 (Coordinated Universal Time) with Vercel.