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

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.

If we cant' build the hardware fast enough. Can someone explain to me why there's apparently 50% of the gpu and memory that hyperscalers buy sitting in warehouses due to lack of data centers? The hyperscalers are hoarding tech and can't even use it. It's ridiculous.

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

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

This looks very interesting. Their new language modelling objective shows some large improvements over masked diffusion modeling.

However, they hardly compare against the conventional next-token-prediction objective, which suggests they don't beat it, except for highly non-linear tasks like sudoku. Unfortunately, machine learning papers often tend to focus exclusively on the positives without mentioning bad aspects.

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.

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

[flagged]

[dead]

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.