April 15, 2025 front

ML Newsnew | past | best | rss | submit

Stories from April 15, 2025 (UTC)

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

1.	Teuken-7B-Base and Teuken-7B-Instruct: Towards European LLMs (2024) (arxiv.org)
	248 points by doener on Apr 15, 2025 \| hide \| past \| pdf \| 95 comments
2.	M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models (arxiv.org)
	33 points by dpstart01 on Apr 15, 2025 \| hide \| past \| pdf \| 3 comments
3.	Differentially Private Synthetic Data via Foundation Model APIs (arxiv.org)
	3 points by jsenn on Apr 15, 2025 \| hide \| past \| pdf \| 1 comment
4.	Scaling Laws of Synthetic Data for Language Models (arxiv.org)
	2 points by PaulHoule on Apr 15, 2025 \| hide \| past \| pdf \| discuss
5.	Neuromorphic Principles for Efficient Large Language Models on Intel Loihi 2 (arxiv.org)
	1 point by PaulHoule on Apr 15, 2025 \| hide \| past \| pdf \| discuss
6.	A Survey on Structured State Space Sequence (S4) Models (arxiv.org)
	1 point by PaulHoule on Apr 15, 2025 \| hide \| past \| pdf \| discuss
7.	A Block-Wise Pruning Algorithm for Efficient Large Language Model Compression (arxiv.org)
	1 point by PaulHoule on Apr 15, 2025 \| hide \| past \| pdf \| discuss
8.	Memory and Bandwidth Are All You Need for Sharded Data Parallel (arxiv.org)
	1 point by PaulHoule on Apr 15, 2025 \| hide \| past \| pdf \| discuss
9.	What the HellaSwag? On the Validity of Common-Sense Reasoning Benchmarks (arxiv.org)
	1 point by ziptron on Apr 15, 2025 \| hide \| past \| pdf \| discuss