Getting Modular with Language Models: Building, Reusing a Library of Experts for Task Generalization

Microsoft Research Forum | Episode 2 | March 5, 2024
Alessandro Sordoni shared recent efforts on building and re-using large collections of expert language models to improve zero-shot and few-shot generalization to unseen tasks.
See more at aka.ms/ResearchForum-Mar2024

[@MicrosoftResearch]

Join us for a continuous exchange of ideas about research in the era of general AI.
*Register for the Microsoft Research Forum series:* aka.ms/ForumRegYT

[@RomanIsraeli]

Thank you for the talk and the work, is there a paper due to be out?

[@MicrosoftResearch]

More info on this particular session including related resources can be found here: www.microsoft.com/en-us/research/quarterly-brief/mar-2024-brief/articles/getting-modular-with-language-models-building-and-reusing-a-library-of-experts-for-task-generalization/

[@LukosPC]

Hi, yes we will be releasing the paper very soon :)