#06 Exploring Large multimodal models in healthcare - GPT-4V, Google PaLI-3 explained
MP3•Episode home
Manage episode 428686723 series 3585389
Content provided by Dev and Doc. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Dev and Doc or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.
🤖Dev and doc👨🏻⚕️ introduces large multimodal models. ✨ The potential of LMMs combining text and images seem limitless, but what's the catch? Dev and Doc is a Podcast where developers and doctors join forces to deep dive into AI in healthcare. Together, we can build models that matter. 👨🏻⚕️Doc - Dr. Joshua Au Yeung - https://www.linkedin.com/in/dr-joshua-auyeung/ 🤖Dev - Zeljko Kraljevic https://twitter.com/zeljkokr 00:00 start 00:32 intro 02:20 what is multimodality? And what are the potentials? 09:43 Large multimodal models paper deep dive (radiology) 18:43 paper deep dive 2 (pathology) 20:40 large multimodal models technical overview, exploration of other LMMs 31:40 Foundational models explanation 35:18 the model transparency index 36:20 Google PaLI-3, light weight models vs large Foundational models 43:04 Summary 44:15 the problems and work to be done for LMMs - hallucinations, inconsistencies, biases, security 49:20 A call for better evidence generation and trials with LMMs 53:00 final points - improving visual spatial recognition, thoughts for future The podcast 🎙️ 🔊Spotify: https://open.spotify.com/show/3QO5Lr3w4Rd6lqwlfKDaB7?si=e7915d844994403e 📙Substack: https://aiforhealthcare.substack.com/ 🎞️ Editor- Dragan Kraljević https://www.instagram.com/dragan_kraljevic/ 🎨Brand design and art direction - Ana Grigorovici https://www.behance.net/anagrigorovici027d
…
continue reading
23 episodes