July 14, 2025 front

ML Newsnew | past | best | rss | submit

Stories from July 14, 2025 (UTC)

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

1.	Persona Features Control Emergent Misalignment (arxiv.org)
	6 points by Bluestein on Jul 14, 2025 \| hide \| past \| pdf \| discuss
2.	ETT: Expanding the Long Context Understanding Capability of LLMs at Test-Time (arxiv.org)
	4 points by PaulHoule on Jul 14, 2025 \| hide \| past \| pdf \| discuss
3.	Lessons from a Chimp: AI "Scheming" and the Quest for Ape Language (arxiv.org)
	2 points by FergusArgyll on Jul 14, 2025 \| hide \| past \| pdf \| discuss
4.	Strategic Intelligence in LLMs: Evidence from Evolutionary Game Theory (arxiv.org)
	2 points by ArmageddonIt on Jul 14, 2025 \| hide \| past \| pdf \| discuss
5.	One Token to Fool LLM-as-a-Judge (arxiv.org)
	2 points by simonpure on Jul 14, 2025 \| hide \| past \| pdf \| discuss
6.	MemOS is a breakthrough "memory operating system" for AI (arxiv.org)
	2 points by amirkabbara on Jul 14, 2025 \| hide \| past \| pdf \| discuss
7.	ASK HN: Why Google's Gemini 2.5 paper has 3295 authors? (arxiv.org)
	2 points by tzury on Jul 14, 2025 \| hide \| past \| pdf \| 4 comments
8.	Cats Confuse LLM: Query Agnostic Adversarial Triggers for Reasoning Models (arxiv.org)
	1 point by DyslexicAtheist on Jul 14, 2025 \| hide \| past \| pdf \| discuss