Large Language Diffusion Models · HackerPapers discussions

Large Language Diffusion Models — HN submission

Wed, 25 Feb 2026 14:31:29 GMT

Large Language Diffusion Models

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Large Language Diffusion Models — mentioned by naasking

Fri, 20 Feb 2026 21:43:23 GMT

I was thining of something like LLaDa that uses a Transformer to predict forward masked tokens: https://arxiv.org/abs/2502.09992

Paper and discussion history. A mention is not an endorsement.

Large Language Diffusion Models — mentioned by StriverGuy

Thu, 01 May 2025 14:26:27 GMT

Related paper discussing diffusion models from 2 months ago: https://arxiv.org/abs/2502.09992

Paper and discussion history. A mention is not an endorsement.

Large Language Diffusion Models — mentioned by kadushka

Sat, 05 Apr 2025 16:16:54 GMT

There are LLMs which do not generate one token at a time: https://arxiv.org/abs/2502.09992 They do not reason significantly better than autoregressive LLMs. Which makes me question “one token at a time” as the bottleneck. Also, Lecun has been pushing his JEPA idea for years now - with not much to show for it. With his resources one could hope we would see the benefits of that over the current state of the art models.

Paper and discussion history. A mention is not an endorsement.

Large Language Diffusion Models — mentioned by hnfong

Fri, 14 Mar 2025 18:29:28 GMT

I'm not an insider and I'm not sure whether this is directly related to "energy minimization", but "diffusion language models" have apparently gained some popularity in recent weeks. https://arxiv.org/abs/2502.09992 https://www.inceptionlabs.ai/news (these are results from two different teams/orgs) It sounds kind of like what you're describing, and nobody else has mentioned it yet, so take a look and see whether it's relevant.

Paper and discussion history. A mention is not an endorsement.

Large Language Diffusion Models — mentioned by kadushka

Wed, 12 Mar 2025 15:43:38 GMT

I don’t know which text diffusion models you’re talking about, the latest and greatest is this one: https://arxiv.org/abs/2502.09992 and it’s extremely slow – couple of orders of magnitude slower than a regular LLM, mainly because it does not support KV caching, and requires many full sequence processing steps per token.

Paper and discussion history. A mention is not an endorsement.

Large Language Diffusion Models — mentioned by mistrial9

Thu, 06 Mar 2025 23:51:09 GMT

this is the huggingface page https://huggingface.co/papers/2502.09992

Paper and discussion history. A mention is not an endorsement.

Large Language Diffusion Models — HN submission

Thu, 27 Feb 2025 00:09:35 GMT

Diffusion LLM Has Arrived

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Large Language Diffusion Models — HN submission

Sun, 23 Feb 2025 19:47:32 GMT

Large Language Diffusion Models

7 points; 3 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Large Language Diffusion Models — mentioned by Kye

Fri, 21 Feb 2025 19:01:44 GMT

A toddler can learn by trial and error mid-process. An LLM using autoregressive inference can only compound errors. The LLDM model paper was posted elsewhere, but: https://arxiv.org/pdf/2502.09992 It basically uses the image generation approach of progressively refining the entire thing at once, but applied to text. It can self-correct mid-process. The blog post where I found it originally that goes into more detail and raises some issues with it: https://timkellogg.me/blog/2025/02/17/diffusion

Paper and discussion history. A mention is not an endorsement.

Large Language Diffusion Models — mentioned by betula_ai

Fri, 21 Feb 2025 18:50:35 GMT

Thank you for this informative and thoughtful post. An interesting twist to the increasing error accumulation as autoregressive models generate more output, is the recent success of language diffusion models for predicting multiple tokens simultaneously. They have a remasking strategy at every step of the reviser process, that masks low confidence tokens. Regardless your observations perhaps still apply. https://arxiv.org/pdf/2502.09992

Paper and discussion history. A mention is not an endorsement.

Large Language Diffusion Models — HN submission

Mon, 17 Feb 2025 05:31:16 GMT

Large Language Diffusion Models

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.