Converting In-Context Learning to Weights in Linearized-Attention Transformers | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		Converting In-Context Learning to Weights in Linearized-Attention Transformers (arxiv.org)
		4 points by PaulHoule on June 15, 2024 \| hide \| past \| favorite \| 1 comment

jonrouach on June 15, 2024 [–]

is that a method to save context tokens by "baking" the attended in-context-learned into the weights? Im missing one step of so-what in the paper abstract..

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact