What is a visual language model (VLM)? What is the next phase of technology for medical diagnostics? This episode of Real Talk explores those two questions—and more!
With many artificial intelligence (AI) terms thrown around, it can be difficult to differentiate one from another. Visual language models are extensions of large language models (LML), combining two key components: a vision component and a language model. This means the technology is able to process both text and images. In this episode of Real Talk, Professional Co-Editor Rehan Ahmed, MD, explains exactly how VLMs work, as well as what technology he thinks is in the pipeline.
From there, Professional Co-Editor Scot Morris, OD, poses an important question for eye care providers to be thinking about: What is next in diagnostic technology? Perhaps more importantly, how will new technology impact what providers do?
Listen to the full discussion here:
Listen to all episodes of Real Talk here
Subscribe to Real Talk on Apple Podcasts and Spotify
Author
