October 9, 2025 front

ML Newsnew | past | best | rss | submit

Stories from October 9, 2025 (UTC)

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

1.	Generalized Orders of Magnitude (arxiv.org)
	45 points by leokoz8 360 days ago \| hide \| past \| pdf \| 12 comments
2.	DeepMind's paper reveals Google's new direction on RAG: In-Context Retreival (arxiv.org)
	6 points by mingtianzhang 359 days ago \| hide \| past \| pdf \| 1 comment
3.	Agentic Context Engineering (arxiv.org)
	4 points by oldfuture 359 days ago \| hide \| past \| pdf \| discuss
4.	Agentic Context Engineering: Evolving Contexts for Self-Improving LMs (arxiv.org)
	4 points by simonpure 360 days ago \| hide \| past \| pdf \| discuss
5.	Can Large Language Models Develop Gambling Addiction? (arxiv.org)
	3 points by speckx 359 days ago \| hide \| past \| pdf \| 1 comment
6.	Hybrid Architectures for Language Models: Systematic Analysis & Design Insights (arxiv.org)
	2 points by matt_d 359 days ago \| hide \| past \| pdf \| discuss
7.	Emergent Misalignment When LLMs Compete for Audiences (arxiv.org)
	1 point by redbell 359 days ago \| hide \| past \| pdf \| discuss
8.	Opening the Black Box: Interpretable LLMs via Semantic Resonance Architecture (arxiv.org)
	1 point by PaulHoule 359 days ago \| hide \| past \| pdf \| discuss
9.	MultimodalHugs: Enabling Sign Language Processing in Hugging Face (arxiv.org)
	1 point by PaulHoule 360 days ago \| hide \| past \| pdf \| discuss
10.	Evaluating LLM Generated Detection Rules in Cybersecurity (arxiv.org)
	1 point by jkamdjou 360 days ago \| hide \| past \| pdf \| discuss
11.	Self-Correction Bench: Revealing and Addressing LLM Self-Correction Blind Spot (arxiv.org)
	1 point by yubblegum 360 days ago \| hide \| past \| pdf \| 2 comments