Portrait de Naoto Usuyama

Naoto Usuyama

Principal Researcher

Connect on LinkedIn

Nouvelles et reportages

A visual illustration of Medprompt performance on the MedQA benchmark. Moving from left to right on a horizontal line, the illustration shows how different Medprompt components and additive contributions improve accuracy starting with zero-shot at 81.7 accuracy, to random few-shot at 83.9 accuracy, to random few-shot, chain-of-thought at 87.3 accuracy, to kNN, few-shot, chain-of-thought at 88.4 accuracy, to ensemble with choice shuffle at 90.2 accuracy.
Blog de recherche Microsoft

| Eric Horvitz, Harsha Nori, et Naoto Usuyama

Discover the most effective run-time strategies on the OpenAI o1-preview model, improving accuracy in medical language tasks.

Digital pathology helps decode tumor microenvironments for precision immunotherapy. GigaPath is a novel vision transformer that can scale to gigapixel whole-slide images by adapting dilated attention for digital pathology. In joint work with Providence and UW, we’re sharing Prov-GigaPath, the first whole-slide pathology foundation model pretrained on large-scale real-world data, for advancing clinical research and discovery.
Blog de recherche Microsoft

| Hoifung Poon et Naoto Usuyama

Digital pathology helps decode tumor microenvironments for precision immunotherapy. In joint work with Providence and UW, we’re sharing Prov-GigaPath, the first whole-slide pathology foundation model, for advancing clinical research.

Dans l’actualité | GeekWire

Researchers at Microsoft, Providence Health System and the University of Washington say they’ve developed a new artificial intelligence model for diagnosing cancer, based on an analysis of more than a billion images of tissue samples from more than 30,000 patients.…

Chris Bishop at Research Forum
Blog de recherche Microsoft

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 of foundational AI technologies.

Dans l’actualité | VentureBeat

In a paper published on the preprint server Arxiv.org, Microsoft researchers propose an AI technique they call domain-specific language model pretraining for biomedical natural language processing (NLP). By compiling a “comprehensive” biomedical (NLP) benchmark from publicly available data sets, the coauthors claim they managed to…