May 24, 2024 front

ML Newsnew | past | best | rss | submit

Stories from May 24, 2024 (UTC)

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

1.	Thermodynamic Natural Gradient Descent (arxiv.org)
	200 points by jasondavies on May 24, 2024 \| hide \| past \| pdf \| 32 comments
2.	You Only Cache Once: Decoder-Decoder Architectures for Language Models (arxiv.org)
	3 points by belter on May 24, 2024 \| hide \| past \| pdf \| discuss
3.	YOLOv10: Real-Time End-to-End Object Detection (arxiv.org)
	2 points by zerojames on May 24, 2024 \| hide \| past \| pdf \| discuss
4.	A Declarative System for Optimizing AI Workloads (arxiv.org)
	2 points by zerojames on May 24, 2024 \| hide \| past \| pdf \| discuss
5.	Axiomatic Attribution for Deep Networks (2017) (arxiv.org)
	2 points by fzliu on May 24, 2024 \| hide \| past \| pdf \| discuss
6.	Bird's-Eye View to Street-View: A Survey (arxiv.org)
	1 point by PaulHoule on May 24, 2024 \| hide \| past \| pdf \| discuss
7.	"Yes I Would Recommend Calling the Police":Norm Inconsistency in LLM Decisions (arxiv.org)
	1 point by belter on May 24, 2024 \| hide \| past \| pdf \| discuss
8.	Lessons from the Trenches on Reproducible Evaluation of Language Models (arxiv.org)
	1 point by tosh on May 24, 2024 \| hide \| past \| pdf \| discuss
9.	Representation noising effectively prevents harmful fine-tuning on LLMs (arxiv.org)
	1 point by darosati on May 24, 2024 \| hide \| past \| pdf \| discuss