How Does In-Context Learning Help Prompt Tuning?
Biomedical Visual-Language Processing (BioViL)
BioViL is a machine learning model trained on biomedical vision and language datasets at scale. It does not require manual annotations and can leverage historical raw clinical image acquisitions and clinical notes.
CodaMosa
This repository contains the code for CodaMOSA. CodaMOSA integrates queries to a Large Language Model (currently supports the OpenAI API) into search-based algorithms for unit test generation.
Research Focus: Week of January 23, 2023
Welcome to Research Focus, a new series of blog posts that highlights notable publications, events, code/datasets, new hires and other milestones from across the research community at Microsoft. Organizations must digitize various documents, many with…
Project Diviner
Dated back in the Shang dynasty, the oracle bone script is the oldest form of Chinese language engraved on animal bones. A large body of the characters and writings still remains mysterious and awaits to…