Training language models with pause tokens (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: Training language models with pause tokens

First screen, captured 3 years ago.

Looks similar

Screenshot of arxiv.org: Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking (arxiv.org)

245 points by hackerlight 2 years ago | 222 comments

Screenshot of arxiv.org: TiDAR: Think in Diffusion, Talk in Autoregression

TiDAR: Think in Diffusion, Talk in Autoregression (arxiv.org)

111 points by internetguy 11 months ago | 18 comments

Screenshot of arxiv.org: Training LLMs to Reason in a Continuous Latent Space

Training LLMs to Reason in a Continuous Latent Space (arxiv.org)

265 points by omarsar 1 year ago | 93 comments

Screenshot of arxiv.org: Language models as compilers: Simulating pseudocode execution

Language models as compilers: Simulating pseudocode execution (arxiv.org)

159 points by milliondreams 2 years ago | 49 comments

Screenshot of arxiv.org: Continuous Autoregressive Language Models

Continuous Autoregressive Language Models (arxiv.org)

98 points by Anon84 11 months ago | 7 comments

Screenshot of arxiv.org: Procedural knowledge in pretraining drives reasoning in large language models

Procedural knowledge in pretraining drives reasoning in large language models (arxiv.org)

232 points by reqo 1 year ago | 96 comments