June 13, 2023 front

ML Newsnew | past | best | rss | submit

Stories from June 13, 2023 (UTC)

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

1.	The Curse of Recursion: Training on Generated Data Makes Models Forget (arxiv.org)
	170 points by indus on Jun 13, 2023 \| hide \| past \| pdf \| 117 comments
2.	Thinking Like Transformers (2021) [pdf] (arxiv.org)
	112 points by jbay808 on Jun 13, 2023 \| hide \| past \| pdf \| 20 comments
3.	Augmenting Language Models with Long-Term Memory (arxiv.org)
	32 points by tosh on Jun 13, 2023 \| hide \| past \| pdf \| 1 comment
4.	Benchmarking Neural Network Training Algorithms (arxiv.org)
	3 points by tim_sw on Jun 13, 2023 \| hide \| past \| pdf \| 1 comment
5.	Can Large Language Models Infer Causation from Correlation? (arxiv.org)
	2 points by PaulHoule on Jun 13, 2023 \| hide \| past \| pdf \| discuss
6.	Large Language Models as Tool Makers (arxiv.org)
	1 point by juunge on Jun 13, 2023 \| hide \| past \| pdf \| discuss
7.	Evidence of Meaning in Large Language Models Trained on Programs (arxiv.org)
	1 point by famouswaffles on Jun 13, 2023 \| hide \| past \| pdf \| discuss
8.	FinGPT: Open-Source Financial Large Language Models (arxiv.org)
	1 point by Anon84 on Jun 13, 2023 \| hide \| past \| pdf \| discuss
9.	Weakly supervised information extraction from handwritten prescriptions (arxiv.org)
	1 point by lnyan on Jun 13, 2023 \| hide \| past \| pdf \| discuss