February 10, 2025 front

ML Newsnew | past | best | rss | submit

Stories from February 10, 2025 (UTC)

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

1.	Scaling up test-time compute with latent reasoning: A recurrent depth approach (arxiv.org)
	149 points by timbilt on Feb 10, 2025 \| hide \| past \| pdf \| 44 comments
2.	Frontier AI systems have surpassed the self-replicating red line (arxiv.org)
	10 points by ryan_j_naughton on Feb 10, 2025 \| hide \| past \| pdf \| 4 comments
3.	LLM Failure Modes in Medical QA Arising from Inflexible Reasoning (arxiv.org)
	3 points by docere on Feb 10, 2025 \| hide \| past \| pdf \| discuss
4.	The Impact of Prompt Programming on Function-Level Code Generation (arxiv.org)
	3 points by bobrenjc93 on Feb 10, 2025 \| hide \| past \| pdf \| discuss
5.	s1: Simple Test-Time Scaling (arxiv.org)
	2 points by btilly on Feb 10, 2025 \| hide \| past \| pdf \| discuss
6.	Adaptive Computation Time for Recurrent Neural Networks (2016) (arxiv.org)
	2 points by tosh on Feb 10, 2025 \| hide \| past \| pdf \| discuss
7.	Self-Backtracking for Boosting Reasoning of LLMs (arxiv.org)
	1 point by omarsar on Feb 10, 2025 \| hide \| past \| pdf \| discuss
8.	ZebraLogic: On The Scaling Limits Of LLMs For Logical Reasoning (arxiv.org)
	1 point by optimalsolver on Feb 10, 2025 \| hide \| past \| pdf \| 1 comment
9.	Scaling Up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach (arxiv.org)
	1 point by tosh on Feb 10, 2025 \| hide \| past \| pdf \| discuss