May 1, 2023 front

ML Newsnew | past | best | rss | submit

Stories from May 1, 2023 (UTC)

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

1.	Are emergent abilities of large language models a mirage? (arxiv.org)
	154 points by chewxy on May 1, 2023 \| hide \| past \| pdf \| 130 comments
2.	It is all about where you start: Text-to-image generation with seed selection (arxiv.org)
	3 points by tim_sw on May 1, 2023 \| hide \| past \| pdf \| discuss
3.	The internal state of an LLM knows when it is lying (arxiv.org)
	3 points by PaulHoule on May 1, 2023 \| hide \| past \| pdf \| discuss
4.	CancerGPT: Few-Shot Drug Pair Synergy Prediction Using Large Pre-Trained Models (arxiv.org)
	2 points by birriel on May 1, 2023 \| hide \| past \| pdf \| discuss
5.	GPTQ Accurate Post-Training Quantization for Generative Pre-Trained Transformers (arxiv.org)
	2 points by tosh on May 1, 2023 \| hide \| past \| pdf \| discuss
6.	Dissecting Recall of Factual Associations in Auto-Regressive Language Models (arxiv.org)
	1 point by tosh on May 1, 2023 \| hide \| past \| pdf \| discuss
7.	Scaling Language Models: Methods, Analysis and Insights from Training Gopher (arxiv.org)
	1 point by tosh on May 1, 2023 \| hide \| past \| pdf \| discuss
8.	Uncertainty-Aware Code Suggestions by Maxing Utility Across Random User Intents (arxiv.org)
	1 point by tim_sw on May 1, 2023 \| hide \| past \| pdf \| discuss