September 20, 2024 front

ML Newsnew | past | best | rss | submit

Stories from September 20, 2024 (UTC)

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

1.	Training Language Models to Self-Correct via Reinforcement Learning (arxiv.org)
	230 points by weirdcat on Sep 20, 2024 \| hide \| past \| pdf \| 92 comments
2.	Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models (arxiv.org)
	20 points by mfiguiere on Sep 20, 2024 \| hide \| past \| pdf \| 3 comments
3.	Breaking ReCAPTCHAv2 (arxiv.org)
	5 points by GaggiX on Sep 20, 2024 \| hide \| past \| pdf \| discuss
4.	Kolmogorov-Arnold Transformer (arxiv.org)
	2 points by GaggiX on Sep 20, 2024 \| hide \| past \| pdf \| discuss
5.	The consistent reasoning paradox of intelligence and optimal trust in AI (arxiv.org)
	1 point by zhamisen on Sep 20, 2024 \| hide \| past \| pdf \| 1 comment
6.	Ranking of popular image generation AI models (incl. Flux) from 2M votes (arxiv.org)
	1 point by maalber on Sep 20, 2024 \| hide \| past \| pdf \| 1 comment
7.	To CoT or not to CoT? Chain-of-thought helps on math and symbolic reasoning (arxiv.org)
	1 point by healthypunk on Sep 20, 2024 \| hide \| past \| pdf \| discuss