Naoto Usuyama的肖像

Naoto Usuyama

Principal Researcher

Connect on LinkedIn

新闻与深度文章

background pattern
微软研究院博客

| Hoifung Poon, Jeya Maria Jose Valanarasu, Naoto Usuyama, 和 Sheng Wang

Using AI-generated virtual populations, …

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.
微软研究院博客

| Eric Horvitz, Harsha Nori, 和 Naoto Usuyama

Discover the most effective run-time str…

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.
微软研究院博客

| Hoifung Poon 和 Naoto Usuyama

Digital pathology helps decode tumor mic…

新闻报道 | GeekWire

Microsoft, Providence and UW make use of generative AI for digital cancer diagnosis 

Researchers at Microsoft, Providence Hea…

Chris Bishop at Research Forum
微软研究院博客

Research advances are driving real-world…

新闻报道 | VentureBeat

Microsoft researchers claim ‘state-of-the-art’ biomedical NLP model 

In a paper (opens in new tab) published …