Stealing Part of a Production Language Model
ICML 2024
Microsoft is proud to be a sponsor of The International Conference on Machine Learning (ICML) (opens in new tab), a premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known…
DNATagging
An implementation of data encoding and decoding using DNA Tags and paper tickets. The api directory contains implementations for REST API endpoints to enable a DNA Tagging application. The test directory contains configurations and tests…
Final intern talk: Distilling Self-Supervised-Learning-Based Speech Quality Assessment into Compact
Speaker: Benjamin StahlHost: Hannes Gamper In this talk, we explore advancements in computational models for speech quality assessment. Self-supervised learning models have emerged as powerful front-ends, outperforming supervised-only models. However, their large size renders them…
Abstracts: July 18, 2024
Senior Researcher Arindam Mitra introduces AgentInstruct. Using raw data sources, the automated multi-agent framework can create diverse, high-quality synthetic data at scale for the post-training of small and large language models.