November 7, 2023 front

ML Newsnew | past | best | rss | submit

Stories from November 7, 2023 (UTC)

Go back a day, month, or year. Go forward a day.

1.	Pretraining data enables narrow selection capabilities in transformer models (arxiv.org)
	65 points by hislaziness on Nov 7, 2023 \| hide \| past \| pdf \| 109 comments
2.	ChipNeMo: Domain-Adapted LLMs for Chip Design (arxiv.org)
	50 points by RafelMri on Nov 7, 2023 \| hide \| past \| pdf \| 7 comments
3.	Taken out of context: On measuring situational awareness in LLMs (arxiv.org)
	2 points by famouswaffles on Nov 7, 2023 \| hide \| past \| pdf \| discuss
4.	Parameters Is All You Need: Tiny Neural Networks for Particle Physics (arxiv.org)
	2 points by PaulHoule on Nov 7, 2023 \| hide \| past \| pdf \| discuss
5.	Knowledge Editing for Large Language Models: A Survey (arxiv.org)
	2 points by PaulHoule on Nov 7, 2023 \| hide \| past \| pdf \| discuss
6.	CogVLM: Visual Expert for Pretrained Language Models (arxiv.org)
	2 points by wawayanda on Nov 7, 2023 \| hide \| past \| pdf \| discuss
7.	Learning in High Dimension Always Amounts to Extrapolation (arxiv.org)
	1 point by tosh on Nov 7, 2023 \| hide \| past \| pdf \| 1 comment
8.	Grokking in Linear Estimators – A Solvable Model Groks Without Understanding (arxiv.org)
	1 point by PaulHoule on Nov 7, 2023 \| hide \| past \| pdf \| 1 comment
9.	CleanCoNLL: A Nearly Noise-Free Named Entity Recognition Dataset (arxiv.org)
	1 point by PaulHoule on Nov 7, 2023 \| hide \| past \| pdf \| discuss