April 8, 2025 front

ML Newsnew | past | best | rss | submit

Stories from April 8, 2025 (UTC)

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

1.	Can reinforcement learning for LLMs scale beyond math and coding tasks? Probably (arxiv.org)
	6 points by GabrielBianconi on Apr 8, 2025 \| hide \| past \| pdf \| 4 comments
2.	Real-Time Evaluation Models for RAG: Who Detects Hallucinations Best? (arxiv.org)
	3 points by s1l3nt on Apr 8, 2025 \| hide \| past \| pdf \| 1 comment
3.	Rope to Nope and Back Again: A New Hybrid Attention Strategy (arxiv.org)
	3 points by ydnyshhh on Apr 8, 2025 \| hide \| past \| pdf \| discuss
4.	SmolVLM: Redefining small and efficient multimodal models (arxiv.org)
	2 points by wertyk on Apr 8, 2025 \| hide \| past \| pdf \| discuss
5.	Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad (arxiv.org)
	2 points by ydnyshhh on Apr 8, 2025 \| hide \| past \| pdf \| discuss
6.	Rethinking Reflection in Pre-Training (arxiv.org)
	1 point by swyx on Apr 8, 2025 \| hide \| past \| pdf \| discuss
7.	Are Domain-Specific Trade-Offs Undermining On-Device Language Models? (arxiv.org)
	1 point by PaulHoule on Apr 8, 2025 \| hide \| past \| pdf \| discuss
8.	InfiniteICL: Breaking the Limit of Context Window Size (arxiv.org)
	1 point by demirbey05 on Apr 8, 2025 \| hide \| past \| pdf \| discuss