Everyone’s health and wellness journey is unique, and AI can help create more personalized health experiences to match this individuality. We're researching how fine-tuning Gemini models for personal health and wellness can unlock novel insights and interactions for consumers. Imagine an AI that not only understands your health data from wearables but also gives you personalized insights and recommendations, like a virtual health coach. Our two new research papers explore this in depth: Towards a Personal Health Large Language Model (PH-LLM): We've fine-tuned Gemini models to create PH-LLM, which generates personalized sleep and fitness recommendations comparable to human experts. Transforming Wearable Data into Personal Health Insights using Large Language Model Agents: This agent system leverages code generation and information retrieval to analyze your wearable data, providing detailed insights into your health patterns. These advances demonstrate how AI can help us better understand our health data and make more informed decisions about our well-being. We look forward to continuing research into how generative AI can enable novel health experiences. Learn more at our blog: https://goo.gle/3RnwHbl #AI #healthcare #wearables #personalizedhealth #GoogleResearch #GoogleAI
About us
From conducting fundamental research to influencing product development, our research teams have the opportunity to impact technology used by billions of people every day. We aspire to make discoveries that impact everyone, and sharing our research and tools to fuel progress in the field is fundamental to our approach.
- Website
-
https://research.google/
External link for Google Research
- Industry
- Technology, Information and Internet
- Company size
- 1,001-5,000 employees
Updates
-
We’re shining a spotlight on Google Researchers and their achievements. ⭐️ Read the full article to learn all about Tiffany Martin Deng's role, mission, and commitment to doing good for all.
-
Vivek Natarajan is a Research Lead working with Google Health AI at the intersection of AI and biomedicine. ⚕️🧡 Learn about project AMIE, Google’s Articulate Medical Intelligence Explorer, a multimodal conversational AI physician-scientist build, that aims to improve the understanding of human biology and scale world-class healthcare to all. 👀➡️ https://goo.gle/45j21NW
-
Today on the blog, read all about how we are bringing together the latest foundation models and software development data to assist with software engineering at Google, including what we’ve learned and where we expect the next wave of this work to go. →https://goo.gle/45fFa5X
-
Machine learning models show great potential as assistive tools in healthcare. Here we present a framework to help ensure medical imaging models are developed responsibly by better understanding how they come to their predictions. The framework leverages generative AI paired with expert review to identify and interpret visual cues associated with model outputs. https://goo.gle/3V9i3oZ
-
Today we present new solutions to the Liner Shipping Network Design and Scheduling Problem, released as part of our new Shipping Network Design API, with the goal of maximizing the efficiency of container shipping networks at world-wide scale. Read more → https://goo.gle/3X61X1Z
-
Learn how the Adversarial Nibbler challenge provides the holistic evaluation of generative text-to-image model robustness against harmful image generation & long-tail safety issues, by using community-driven red teaming to build a diverse set of harmful prompts. https://goo.gle/3X2D9Ik
-
Meet Laura Vardoulakis, a Sr. Staff UX Researcher whose mission is to improve the lives of people through health-centered research. 🏥💡 → https://goo.gle/3yH2b5P Learn about the insightful research that’s being conducted with AI models in the world of healthcare as a means of improving the user experience for a more efficient and effective system.
-
Instruction tuning can help align LLMs with an intended objective, but success often requires quality data tailored to specific tasks. Learn how a novel framework, CodecLM, systematically generates tailored high-quality data to align LLMs to specific tasks →https://goo.gle/4c0aGah