The Office of the Chief Scientific Officer works with senior leadership at Microsoft on strategy and opportunities at the frontiers of science and engineering. We are seeking Research Intern applications for spring, summer, or fall…
Microsoft Research Health Futures UK conducts world-class research at the intersection of AI and healthcare, drawing on deep expertise in biomedical imaging and multimodal deep learning. We are seeking a motivated postdoctoral researcher to join…
Microsoft Research Health Futures UK conducts world-class research at the intersection of AI and healthcare, drawing on deep expertise in biomedical imaging and multimodal deep learning. We are seeking research interns to join our vibrant…
Discover the most effective run-time strategies on the OpenAI o1-preview model, improving accuracy in medical language tasks.
Our organization, Microsoft Health Futures, is an interdisciplinary group of researchers, data scientists, computational biologists, bioinformaticians, engineers, physicians, and user experience researchers who are working to accelerate biomedical discovery. We apply the design thinking process…
RAD-DINO is a vision transformer model trained to encode chest X-rays using the self-supervised learning method DINOv2. RAD-DINO is described in detail in RAD-DINO: Exploring Scalable Medical Image Encoders Beyond Text Supervision (F. Pérez-García, H. Sharma, S.…
MAIRA-2 is a multimodal transformer designed for the generation of grounded or non-grounded radiology reports from chest X-rays. It is described in more detail in MAIRA-2: Grounded Radiology Report Generation (S. Bannur, K. Bouzid et al.,…
RadFact is a framework for the evaluation of model-generated radiology reports given a ground-truth report, with or without grounding. Leveraging the logical inference capabilities of large language models, RadFact is not a single number but a suite of…
