Research talk: Differentially private fine-tuning of large language models

About this video

Advanced · Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidence

Explains differential privacy techniques applied to fine-tuning large language models, a concrete security method in modern AI. Research talk format with technical depth suitable for computer science education.

A 36-minute video from Microsoft Research: “Research talk: Differentially private fine-tuning of large language models”.

Video by Microsoft Research, played through YouTube's embedded player.