Microsoft Research AI updates

What if pathology foundation models could do more with less?

MindTopo sets a new benchmark for testing how AI understands topological relationships and highlights new opportunities to strengthen spatial reasoning and planning.

Radiology AI is evolving beyond report generation.

Orchard is an open-source framework for the research community to train and evaluate AI agents across task types.

Computer-use AI agents struggle with multi-step workflows like email and customer support.

Aurora 1.5 adds 22 more variables, hourly temporal resolution, and probabilistic ensemble forecasting to the Aurora foundation model, making it more useful for real-world...

Short chart specifications are easy to write, but often produce uninspiring results.

AI agents often fail because their instructions, or skills, are manually modified with no guarantee of improvement.

AI agents can't remember past conversations.

Researchers introduce generative causal testing, which translates black box models into clear hypotheses and verifies them in the scanner, revealing what specific brain r...