Computer vision
Teaching machines to interpret and reason about the visual world, from object recognition to medical imaging.
Microsoft Research Blog
VidTok introduces compact, efficient tokenization to enhance AI video processing
The VidTok method can enable AI systems to process and generate videos more effectively. Compact tokenization reduces computational costs while maintaining video quality across a potentially diverse set of applications.
Microsoft Research Blog
Research Focus: Week of March 24, 2025
In this issue, we examine a new conversation segmentation method that delivers more coherent and personalized agent conversation, and we review efforts to improve MLLMs’ understanding of geologic maps. Check out the latest research and…
