February 3, 2026 front

ML Newsnew | past | best | rss | submit

Stories from February 3, 2026 (UTC)

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

1.	Linear representations in LLMs can change dramatically over a conversation (arxiv.org)
	5 points by gmays 242 days ago \| hide \| past \| pdf \| discuss
2.	Reasoning Models Generate Societies of Thought (arxiv.org)
	2 points by PaulHoule 242 days ago \| hide \| past \| pdf \| discuss
3.	Exploration Posteriors for Generative Modeling Using Only Negative Rewards (arxiv.org)
	1 point by numeri 242 days ago \| hide \| past \| pdf \| discuss
4.	Revisiting Disaggregated LLM Serving for Performance and Energy Implications (arxiv.org)
	1 point by PaulHoule 242 days ago \| hide \| past \| pdf \| discuss
5.	Language-Related Ideological Divergence in LLM Analysis of Political Documents (arxiv.org)
	1 point by PaulHoule 242 days ago \| hide \| past \| pdf \| discuss
6.	Strategies of cooperation and defection in five large language models (arxiv.org)
	1 point by PaulHoule 242 days ago \| hide \| past \| pdf \| discuss
7.	A Pragmatic VLA Foundation Model (arxiv.org)
	1 point by mountainview 243 days ago \| hide \| past \| pdf \| discuss
8.	PaperBanana: Automating Academic Illustration for AI Scientists (arxiv.org)
	1 point by fzliu 243 days ago \| hide \| past \| pdf \| discuss