June 17, 2025 front

ML Newsnew | past | best | rss | submit

Stories from June 17, 2025 (UTC)

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

1.	AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions (arxiv.org)
	5 points by sjb326 on Jun 17, 2025 \| hide \| past \| pdf \| 2 comments
2.	Scaling On-Device GPU Inference for Large Generative Models (arxiv.org)
	5 points by Anon84 on Jun 17, 2025 \| hide \| past \| pdf \| discuss
3.	Serving Large Language Models on Huawei CloudMatrix384 (arxiv.org)
	3 points by fspeech on Jun 17, 2025 \| hide \| past \| pdf \| discuss
4.	Large Language Models and Emergence: A Complex Systems Perspective (arxiv.org)
	2 points by mathgenius on Jun 17, 2025 \| hide \| past \| pdf \| discuss
5.	Is there a half-life for the success rates of AI agents? (arxiv.org)
	2 points by YeGoblynQueenne on Jun 17, 2025 \| hide \| past \| pdf \| discuss
6.	CURE: A Dataset for Clinical Understanding and Retrieval Evaluation (arxiv.org)
	1 point by fzliu on Jun 17, 2025 \| hide \| past \| pdf \| discuss
7.	Rethinking Text-Based Protein Understanding: Retrieval or LLM? (arxiv.org)
	1 point by PaulHoule on Jun 17, 2025 \| hide \| past \| pdf \| discuss