March 14, 2025 front

ML Newsnew | past | best | rss | submit

Stories from March 14, 2025 (UTC)

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

1.	Block Diffusion: Interpolating between autoregressive and diffusion models (arxiv.org)
	156 points by GaggiX on Mar 14, 2025 \| hide \| past \| pdf \| 32 comments
2.	Predictive Data Selection: The Data That Predicts Is the Data That Teaches (arxiv.org)
	5 points by PaulHoule on Mar 14, 2025 \| hide \| past \| pdf \| discuss
3.	Transformers Without Normalization (arxiv.org)
	4 points by qianli_cs on Mar 14, 2025 \| hide \| past \| pdf \| discuss
4.	PromptPex: Automatic Test Generation for Language Model Prompts (arxiv.org)
	2 points by reshabh on Mar 14, 2025 \| hide \| past \| pdf \| 1 comment
5.	Scaling Laws for DiLoCo (arxiv.org)
	2 points by isof4ult on Mar 14, 2025 \| hide \| past \| pdf \| discuss
6.	A Survey of Long Chain-of-Thought for Reasoning Large Language Models (arxiv.org)
	2 points by belter on Mar 14, 2025 \| hide \| past \| pdf \| discuss
7.	Chain-of-Thought Reasoning in the Wild Is Not Always Faithful (arxiv.org)
	2 points by flyingpumba on Mar 14, 2025 \| hide \| past \| pdf \| discuss
8.	Medical Hallucinations in Foundation Models and Their Impact on Healthcare (arxiv.org)
	1 point by rntn on Mar 14, 2025 \| hide \| past \| pdf \| discuss