May 20, 2024 front

ML Newsnew | past | best | rss | submit

Stories from May 20, 2024 (UTC)

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

1.	26× Faster Inference with Layer-Condensed KV Cache for Large Language Models (arxiv.org)
	127 points by georgehill on May 20, 2024 \| hide \| past \| pdf \| 19 comments
2.	People cannot distinguish GPT-4 from a human in a Turing test (arxiv.org)
	3 points by Paul-Craft on May 20, 2024 \| hide \| past \| pdf \| discuss
3.	Emergent Abilities of Large Language Models (arxiv.org)
	2 points by Anon84 on May 20, 2024 \| hide \| past \| pdf \| discuss
4.	Observational Scaling Laws and the Predictability of Language Model Performance (arxiv.org)
	2 points by belter on May 20, 2024 \| hide \| past \| pdf \| discuss
5.	Training Exact Ambient Diffusion Models with Noisy Data (arxiv.org)
	1 point by rntn on May 20, 2024 \| hide \| past \| pdf \| discuss
6.	Visualizing the Effects of Predictor Variables in Black Box Supervised Models (arxiv.org)
	1 point by Anon84 on May 20, 2024 \| hide \| past \| pdf \| discuss
7.	From r to Q∗: Your Language Model is a Q-Function (arxiv.org)
	1 point by zerojames on May 20, 2024 \| hide \| past \| pdf \| discuss
8.	Chameleon: Mixed-Modal Early-Fusion Foundation Models (arxiv.org)
	1 point by rando_person_1 on May 20, 2024 \| hide \| past \| pdf \| discuss