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

Subscribers:
342,000
Published on ● Video Link: https://www.youtube.com/watch?v=oIAmrrAEPE8



Duration: 8:44
561 views
18


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 https://aka.ms/ResearchForum-Mar2024




Other Videos By Microsoft Research


2024-05-10Unlocking Real world solutions with AI – Chris Bishop
2024-05-10How will AI transform precision medicine? – Ava Amini
2024-05-03AI Case Studies for Natural Science Research with Bonnie Kruft
2024-04-29AI For All: Embracing Equity for All
2024-04-24TrustRate: A Decentralized Platform for Hijack-Resistant Anonymous Reviews
2024-04-22Women in Data Science Fireside Chat with Ilda Ladeira, Karin Kimbrough and Lisa Cohen
2024-04-09Combining Machine Learning and Bayesian networks for Decision Support in Arrythmia Diagnosis
2024-03-20Strategic Subset Selection in Satellite Imagery: Machine Vision Insights
2024-03-11Generative AI and Plural Governance: Mitigating Challenges and Surfacing Opportunities
2024-03-11GigaPath: Foundation Model for Digital Pathology
2024-03-11Getting Modular with Language Models: Building, Reusing a Library of Experts for Task Generalization
2024-03-11The Metacognitive Demands and Opportunities of Generative AI
2024-03-11What's new in AutoGen?
2024-03-11Research Forum 2 | Panel Discussion: Transforming the Natural Sciences with AI
2024-03-11Research Forum 2 | Keynote: The Revolution in Scientific Discovery
2024-02-29Connectivity is a thing, is THE thing
2024-01-31Meet the 2024 Microsoft Research AI & Society fellows
2024-01-31Research Forum: Closing Remarks and Announcements
2024-01-31Kahani: Visual Storytelling through Culturally Nuanced Images
2024-01-31Generative AI meets Structural Biology: Equilibrium Distribution Prediction
2024-01-31Augmenting Human Cognition and Decision Making with AI