June 18, 2024 front

ML Newsnew | past | best | rss | submit

Stories from June 18, 2024 (UTC)

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

1.	Refusal in language models is mediated by a single direction (arxiv.org)
	209 points by Tomte on Jun 18, 2024 \| hide \| past \| pdf \| 44 comments
2.	Transcendence: Generative Models Can Outperform the Experts That Train Them (arxiv.org)
	4 points by sanxiyn on Jun 18, 2024 \| hide \| past \| pdf \| discuss
3.	An Image Is Worth 32 Tokens for Reconstruction and Generation (arxiv.org)
	2 points by doener on Jun 18, 2024 \| hide \| past \| pdf \| discuss
4.	Joint Audio and Symbolic Conditioning for Temporally Controlled Text-to-Music (arxiv.org)
	2 points by tzury on Jun 18, 2024 \| hide \| past \| pdf \| discuss
5.	Compositional Generative Modeling: A Single Model Is Not All You Need (arxiv.org)
	2 points by j_maffe on Jun 18, 2024 \| hide \| past \| pdf \| discuss
6.	Depth Anything V2 (arxiv.org)
	2 points by smusamashah on Jun 18, 2024 \| hide \| past \| pdf \| discuss
7.	Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning (arxiv.org)
	1 point by PaulHoule on Jun 18, 2024 \| hide \| past \| pdf \| discuss
8.	Exploring the Latest LLMs for Leaderboard Extraction (arxiv.org)
	1 point by PaulHoule on Jun 18, 2024 \| hide \| past \| pdf \| discuss
9.	LlamaCare: A Large Medical Language Model for Healthcare Knowledge Sharing (arxiv.org)
	1 point by PaulHoule on Jun 18, 2024 \| hide \| past \| pdf \| discuss