Google DeepMind's Gemini Models in Medicine
[This is an in-person event]
Agenda:
5pm – Registration & networking
5:30 – 6:30 Official presentation
6:30 - 8pm Networking
------------------------------------------------------------------
Application of Large Language Models in medicine is probably among the most impactful developments that could change the lives of billions.
At the same time, it's the most challenging application because it requires advanced reasoning, access to up-to-date medical knowledge, and understanding of complex multimodal data.
Google DeepMind's Gemini models, which have advanced general capabilities, showed strong possibilities in the medical domain.
In this in-person BuzzRobot community meetup, researchers from Google DeepMind will talk about Med-Gemini, a family of capable multimodal models that specialize in medicine.
The researchers evaluated Med-Gemini on 14 medical benchmarks, establishing new state-of-the-art (SoTA) performance on 10 of them, and surpass the GPT-4 model family on every benchmark where a direct comparison is viable.
Moreover, Med-Gemini's performance suggests real-world utility by surpassing human experts on tasks such as medical text summarization, alongside demonstrations of promising potential for multimodal medical dialogue, medical research, and education.
Join the BuzzRobot community on Slack
Subscribe to our YouTube channel with previous talks
The paper