A team of computer scientists and engineers at Apple has developed an LLM model that the company claims can interpret both images and data. The group has posted a paper to the arXiv preprint server describing their new MM1 family of multimodal models and test results.
Over the past year, LLMs have received a lot of press for their advanced AI capabilities. One company notably absent from the conversation is Apple. In this new effort, the research team makes it clear that the company is not interested in simply adding an LLM developed by another company (currently they are negotiating with Google to add Gemini AI tech to Apple devices); instead, they have been working to develop a next-generation LLM, one that can interpret both images and text data.
Multimodal AI works by integrating and processing different types of data inputs, such as visual, auditory and textual information. This integration allows the AI to have a more comprehensive understanding of complex data, leading to more accurate and context-aware interpretations than single-mode AI systems.
To read more, click here.