←back to thread

Nested Learning: A new ML paradigm for continual learning

(research.google)
149 points themgt | 1 comments | 07 Dec 25 14:47 UTC | HN request time: 0.194s | source
Show context
Bombthecat ◴[08 Dec 25 11:47 UTC] No.46191193[source]▶
Damn, and before that, Titan from Google: https://research.google/blog/titans-miras-helping-ai-have-lo...

We are not at the end of AI :)

Also, someone claimed that NVIDA combined diffusion and autoregression, making it 6 times faster, but couldn't find a source. Big if true!

replies(1): >>46191256 #
heavymemory ◴[08 Dec 25 11:59 UTC] No.46191256[source]▶
Do you have a source for the NVIDIA “diffusion plus autoregression 6x faster” claim? I can’t find anything credible on that.
replies(2): >>46191331 #>>46191397 #
1. Bombthecat ◴[08 Dec 25 12:10 UTC] No.46191331[source]▶
Me neither, that's why I wrote that someone claimed that they did.

The idea is simple, in a way, with diffusion several sentences / words get predicted, but they usually are not of great quality. With auto regression they select the correct words.

Increasing quality and speed. Sounds a bit like conscious and sub-conscious to me.