Generative AI for Biomedical Applications: Images, Molecules, Wearables, and Conversations скачать в хорошем качестве

Generative AI for Biomedical Applications: Images, Molecules, Wearables, and Conversations

Abstract: This presentation will provide an overview of our work in the machine learning and generative AI space. We will first cover projects leveraging LLMs for interpreting medical modalities spanning imaging to genomic and wearable data. Then, we will cover our work releasing our models as open-weights for the community to build on (https://goo.gle/hai-def), ranging from imaging foundation models to molecular understanding (Tx-Gemma) and multimodal models (MedGemma). Finally, I will cover our work leveraging Gemini to solve challenging clinical cases from NEJM and tackling diagnostic dialogue and more. Bio: Yun Liu is a senior staff research scientist in Google Research. In this role he focuses on developing and validating machine learning for medical applications across multiple fields: pathology, ophthalmology, radiology, dermatology, and more. Yun completed his PhD at Harvard-MIT Health Sciences and Technology, where he worked on predictive risk modeling using biomedical signals, medical text, and billing codes. He has previously also worked on predictive modeling for nucleic acid sequences and protein structures. Yun completed a B.S. in Molecular and Cellular Biology and Computer Science at Johns Hopkins University.