Microsoft Research Lab – Redmond

2024年5月15日

Welcome to Research Focus, a series of blog posts that highlights notable publications, events, code/datasets, new hires and other milestones from across the research community at Microsoft. Large language models (LLMs) have shown remarkable performance in generating text similar to…

2024年5月15日

From immersive virtual experiences to interactive design tools, Microsoft Research is at the frontier of exploring how people engage with technology. Discover our latest breakthroughs in human-computer interaction research at CHI 2024.

2024年5月6日 | Michel Galley 和 Gretchen Huizinga

Researcher Michel Galley explores how he and fellow researchers combined new and existing data to create MathVista, an open-source benchmark for measuring the mathematical reasoning capabilities of foundation models in scenarios that involve text and images.

2024年5月2日

In this edition: Can LLMs transform natural language into formal method postconditions; Semantically aligned question + code generation for automated insight generation; Explaining CLIP performance disparities on blind/low vision data; plus recent news.

2024年4月18日 | Tobias Schnabel 和 Jennifer Neville

SAMMO optimizes prompts for LLMs by leveraging their structure to guide optimization. This minimizes the time and effort needed to find performant prompts on a variety of tasks.

2024年4月17日

In this issue: New research on appropriate reliance on generative AI; Power management opportunities for LLMs in the cloud; LLMLingua-2 improves task-agnostic prompt compression; Enhancing COMET to embrace under-resourced African languages:

2024年4月16日 | Ranveer Chandra

Microsoft at NDSI 2024: Discoveries and implementations in networked systems Topics range from 5G, space, datacenters, and wide-area networking to applications in artificial intelligence, security, video conferencing, and gaming. Learn more about the discoveries and advances we’re making with networked…

2024年4月16日 | Gretchen Huizinga 和 Tusher Chakraborty

Tusher Chakraborty talks about the paper “Spectrumize: Spectrum-efficient Satellite Networks for the Internet of Things,” including a method for supporting communication between a large IoT-satellite constellation and devices on Earth within a limited spectrum.