Tag

Multimodal Llm

All articles tagged with #multimodal llm

"Apple Unveils Groundbreaking Multimodal AI with 30B Parameters for Text and Vision"
technology2 years ago

"Apple Unveils Groundbreaking Multimodal AI with 30B Parameters for Text and Vision"

Apple researchers have developed new methods for training large language models using both text and visual information, resulting in state-of-the-art performance on AI benchmarks. The paper, titled "MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training," discusses the importance of architecture components and data choices in building performant Multimodal Large Language Models (MLLMs). The MM1 model family demonstrates enhanced in-context learning and multi-image reasoning, enabling few-shot chain-of-thought prompting, and produces competitive performance on a wide range of benchmarks.

"Apple Unveils MM1: The Future of Multimodal AI"
technology2 years ago

"Apple Unveils MM1: The Future of Multimodal AI"

Apple researchers have quietly revealed MM1, a set of multimodal large language models designed for captioning images, answering visual questions, and natural language inference. The MM1 family supports up to 30 billion parameters and achieves competitive performance after supervised fine-tuning on established multimodal benchmarks. Apple's work on MM1 indicates a significant advance in AI, and the company is rumored to be working on an LLM framework code-named "Ajax" as part of a $1 billion AI R&D push. Apple is expected to share more details on its AI efforts at the upcoming WWDC developer show in June.