Ideas: Exploring AI frontiers with Rafah Hosn
Energized by disruption, partner group product manager Rafah Hosn is helping to drive scientific advancement in AI for Microsoft. She talks about the mindset needed to work at the frontiers of AI and how the…
TREC Deep Learning Track
The TREC Deep Learning Track studies information retrieval in a large training data regime. This is the case where the number of training queries with at least one positive label is at least in the…
GitHub Publication Publication Publication Publication Publication
Make Your LLM Fully Utilize the Context
Phi-3
The Phi-3-Mini-128K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense…
Project GraphRAG
LLM-Derived Knowledge Graphs GraphRAG (Graphs + Retrieval Augmented Generation) is a technique for richly understanding text datasets by combining text extraction, network analysis, and LLM prompting and summarization into a single end-to-end system. GraphRAG and…
Women in Data Science Fireside Chat with Ilda Ladeira, Karin Kimbrough and Lisa Cohen
Watch the WiDS event — Ilda Ladeira fireside chat with Karin Kimbrough and Lisa Cohen, hosted by Women in Data Science @ Microsoft community on March 21st, 10:30-11:30am PT. The speakers share their career journey,…