October 23, 2024 front

ML Newsnew | past | best | rss | submit

Stories from October 23, 2024 (UTC)

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

1.	Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces (arxiv.org)
	44 points by hislaziness on Oct 23, 2024 \| hide \| past \| pdf \| 15 comments
2.	What Matters in Transformers? Not All Attention Is Needed (arxiv.org)
	3 points by jonbaer on Oct 23, 2024 \| hide \| past \| pdf \| discuss
3.	From Tokens to Words: On the Inner Lexicon of LLMs (arxiv.org)
	2 points by PaulHoule on Oct 23, 2024 \| hide \| past \| pdf \| discuss
4.	We discovered a way to measure LLM bias while building a recruitment tool (arxiv.org)
	1 point by dreamfactored on Oct 23, 2024 \| hide \| past \| pdf \| 1 comment
5.	What makes your model a low-empathy or warmth person? (arxiv.org)
	1 point by PaulHoule on Oct 23, 2024 \| hide \| past \| pdf \| discuss
6.	Remote Timing Attacks on Efficient Language Model Inference (arxiv.org)
	1 point by belter on Oct 23, 2024 \| hide \| past \| pdf \| discuss
7.	Neural Network Quine (Attempt) (arxiv.org)
	1 point by diginova on Oct 23, 2024 \| hide \| past \| pdf \| discuss
8.	Assessing the Performance of Human-Capable LLMs – Are LLMs Coming for Your Job? (arxiv.org)
	1 point by sandwichsphinx on Oct 23, 2024 \| hide \| past \| pdf \| discuss