Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Microsoft Research Blog
UniRG: Scaling medical imaging report generation with multimodal reinforcement learning
AI can help generate medical image reports, but today’s models struggle with varying reporting schemes. Learn how UniRG uses reinforcement learning to boost performance of medical vision-language models.
Publication
Calibration without Ground Truth
Project
AI for Low-Resource Languages
< AI for Good Lab Language is more than communication—it sustains culture, identity, and opportunity. Yet most of the world’s languages remain underrepresented in today’s AI systems because they have limited digital content, few high-quality…
Microsoft Research Blog
Argos: Multimodal reinforcement learning with agentic verifier for AI agents
Argos improves multimodal RL by evaluating whether an agent’s reasoning aligns with what it observes over time. The approach reduces visual hallucinations and produces more reliable, data-efficient agents for real-world applications.
