Next-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation | Hacker News Reader

Next-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation

arxiv.org

That's pretty innovative. But a brand new tokenizer and training method need a lot of effort to do the retraining. Whether it will be widely implemented depends on real frontier performance it can reach.

Who's going to train a nice big coding model based on this? I don't have the GPUs to do it...

I hope Apple Silicon will one day be competitive with GPUs. It dominates much of the CPU market, and it has a GPU, but it's still not even remotely comparable to Nvidia for inference (factor of >5 in some cases, especially in prefill) or even for gaming ("edge computing" in Nvidia terms).

I feel like their GPU architecture is going to need a significant redesign. There are limits to this tile-based mobile architecture.

I'm not sure why but using X instead of the word "times" annoys me. Probably because one of the first things I got taught at university is that mathematical notation is not prose and shouldn't be used as such.

But what about “got taught” instead of “was taught” and the missing comma before “but”?

Well they didn't teach me English. Or in English for that matter.

And I don't think I've ever used the Oxford comma.

There was probably some rule about not beginning sentences with Or and And but you probably know better than I.

The Oxford comma is the comma before the conjunction in a list of three or more terms, e.g. "one, two, and three". I think your sentence actually didn't need a comma anway.

I'm trying to run it, so far no luck

I keep getting clickbait youtube videos about how "NCM" obsoletes "LLMs" and "Nvidia memory chips" (yes, it's that bad).

This makes me wonder what these people think an "LLM" even is. The name itself implies that it is large and about language. It does not imply that an "LLM" is inherently autoregressive or that it has any particular architecture even though most LLMs are transformers. Anything can be a large language model as long as it is large and models language.

NCM is basically a hierarchical diffusion transformer where the further layers take one big token and then generate two smaller tokens. So it is more like an evaluation strategy. You could apply this to any model architecture.

I personally think the name NCM itself is terrible because it contains the word "next" which inherently implies an ordering and somehow we are supposed to think that "LLM" which contains no mention of ordering, is constrained to ordered token production.

I think they think an LLM is just whatever another LLM tells them it is when they ask it to generate a script.

Can we apply any insights from image and video compression and partitioning to this kind of dimensional masking ?

https://www.youtube.com/watch?v=nv5_PH2uPVI

Reply on news.ycombinator.com