Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Microsoft Research Blog
Improving LLM understanding of structured data and exploring advanced prompting methods
Structural Understanding Capabilities is a new benchmark for evaluating and improving LLM comprehension of structured table data. This advance can help LLMs process and analyze data more effectively, broadening their applicability in real-world tasks.
Microsoft Research Blog
Research Forum Episode 2: Transforming health care and the natural sciences, AI and society, and the evolution of foundational AI technologies
Research advances are driving real-world impact faster than ever. Episode 2 of Microsoft Research Forum explores how AI is transforming health care and the natural sciences, the intersection of AI and society, and the evolution…
Microsoft Research Blog
Research Focus: Week of March 4, 2024
In this issue: Generative kaleidoscopic networks; Text diffusion with reinforced conditioning; PRISE – Learning temporal action abstractions as a sequence compression problem.
Video
Using Archai to search for best Face Segmentation model on Azure ML
This video shows how to use the Archai search framework to find the best possible face segmentation model on Azure ML including a check that the models work well on Qualcomm Snapdragon hardware. – 00:00…
Tool
AI Controller Interface (AICI)
The AI Controller Interface is a system design and implementation that enables customer user code (AI Controllers, implemented as light-weight virtual machines) to tightly, efficiently, and securely integrate with LLM decoding in a cloud service.…
Microsoft Research Blog
Orca-Math: Demonstrating the potential of SLMs with model specialization
Microsoft’s Orca-Math, a specialized small language model, outperforms much larger models in solving math problems that require multi-step reasoning and shows the potential of using feedback to improve language models. Learn more.
