January 2, 2025 front

ML Newsnew | past | best | rss | submit

Stories from January 2, 2025 (UTC)

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

1.	TinyStories: How Small Can Language Models Be and Still Speak Coherent English? (2023) (arxiv.org)
	218 points by tzury on Jan 2, 2025 \| hide \| past \| pdf \| 104 comments
2.	Why transformers are obviously good models of language (arxiv.org)
	6 points by jxmorris12 on Jan 2, 2025 \| hide \| past \| pdf \| discuss
3.	Meta: Memory Layers at Scale (arxiv.org)
	4 points by georgehill on Jan 2, 2025 \| hide \| past \| pdf \| discuss
4.	The Overthinking of O1-Like LLMs (arxiv.org)
	3 points by omarsar on Jan 2, 2025 \| hide \| past \| pdf \| 1 comment
5.	MVQ: Efficient DNN Compression and Acceleration with Masked Vector Quantization (arxiv.org)
	2 points by PaulHoule on Jan 2, 2025 \| hide \| past \| pdf \| discuss
6.	Generative Modeling with Explicit Memory (arxiv.org)
	2 points by PaulHoule on Jan 2, 2025 \| hide \| past \| pdf \| discuss
7.	Scaling of Search and Learning (arxiv.org)
	2 points by jonbaer on Jan 2, 2025 \| hide \| past \| pdf \| discuss
8.	Reinforcement Learning for Multi-Intersection Traffic Signal Control (arxiv.org)
	1 point by PaulHoule on Jan 2, 2025 \| hide \| past \| pdf \| discuss