Apple Publishes Details About New 'MM1' AI Model
Apple researchers have developed a new method for training large language models (LLMs) that seamlessly integrates both text and visual information.
The company's findings, detailed in a research paper titled "MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training," showcase a new approach to creating more intelligent and flexible AI systems. By utilizing a diverse dataset comprising image-caption pairs, interleaved image-text documents, and text-only data, Apple's claims that the MM1 model sets a new standard in AI's ability to perform tasks such as image captioning, visual question answering, and natural language inference with a high level of accuracy.
Apple's research focuses on the combination of different types of training data and model architectures, which enables the AI to understand and generate language based on a mix of visual and linguistic cues. This capability is vital for tasks that require a nuanced comprehension of the world, such as interpreting complex images or answering questions that involve visual elements.
The paper also highlights the MM1 model's exceptional in-context learning abilities, particularly in the largest 30 billion parameter configuration of the model. This version apparently exhibits remarkable capabilities for multi-step reasoning over multiple images using few-shot "chain-of-thought" prompting, a technique that allows the AI to perform complex, open-ended problem solving based on minimal examples.
This research emerges as part of Apple's broader initiative to enhance its AI capabilities amid growing competition. Earlier today, Bloomberg's Mark Gurman reported that Apple is in discussions with Google to license Google's Gemini generative large-language models to power new features coming to the iPhone as part of iOS 18.
Popular Stories
Apple's iPhone development roadmap runs several years into the future and the company is continually working with suppliers on several successive iPhone models concurrently, which is why we sometimes get rumored feature leaks so far ahead of launch. The iPhone 17 series is no different, and already we have some idea of what to expect from Apple's 2025 smartphone lineup. If you plan to skip...
When introducing the new M4 iPad Pro models, Apple showed a video of a hydraulic press crushing all manner of creative tools, including musical instruments, electronic equipment, arcade games, paint and brushes, computers, cameras, and more, with the aim of demonstrating how the iPad represents all of the tools condensed into a single device. The ad was a play on the popular hydraulic press...
Today we're tracking multiple record low prices across the M1 iPad Air on Amazon, with $150 off every configuration of these now-discontinued tablets. This comes just a few days after Apple announced the new M2 iPad Air, which start at $599. Note: MacRumors is an affiliate partner with Amazon. When you click a link and make a purchase, we may receive a small payment, which helps us keep the...
Benchmarks for the new M4 iPad Pro models have ">popped up on Geekbench, giving us an idea of how much faster Apple's second-generation 3-nanometer chips are compared to the M3, M2, and other prior-generation Apple silicon chips. The 10-core variant of the M4 chip earned an average single-core score of 3,695 and an average multi-core score of 14,550 across 10 benchmarks. When it comes to...
With the iPad Pro, Apple introduced an overhauled version of the Magic Keyboard to add new features that make using an iPad Pro feel more like using a Mac. If you’re thinking about buying one of the new iPad Pro models and don’t know if you should get a keyboard, this article walks through all of the new features. Design Apple hasn’t changed the underlying look of the Magic Keyboard, and...
Top Rated Comments
Apple hasn't become who they are with such a vast treasure trove of expertise and wealth by sheer dumb luck.