Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
動画
New fine-tuning of language models: Match meaning, not tokens
Language models are usually trained to predict the next word, but that does not always lead to the best overall answers. We introduce energy-based fine-tuning, a new method that trains models to produce better full…
動画
Introducing Interwhen: Steering reasoning agents with real-time verification
What if AI agents could check their work as they go? This verification method extracts verifiable properties from natural language and evaluates them using symbolic or model-based verifiers. Interwhen, a new open-source library, enables real-time…
動画
Introducing GitHub Agentic Workflows: AI that runs your repo
What if your repo could run itself? GitHub Agentic Workflows bring AI agents directly into repository automation, enabling tasks to run end-to-end inside GitHub Actions. With built-in guardrails and Microsoft-hosted models on Azure, this system…
動画
MagenticLite: A full-stack agentic experience powered by Small Models
What if you could run a capable AI agent without leaning on frontier-scale models? MagenticLite is the next generation of Magentic-UI, an agentic experience reimagined and optimized for small language models. It works across both…
プロジェクト
Project Volano
Enabling everyone to shape AI Project Volano is carrying out cross-disciplinary research to understand how we can value and utilize community perspectives throughout the whole of the AI pipeline. Our first use case is to…