What is the new Model of Twelve Labs?
Marengo-2.6: A New State-of-the-Art Video Foundation Model
Hey Everyone,
Twelve Labs is a Korean-American startup that has really caught my attention. They build foundational model around video search for example, and as multi-modal AI evolves this is going to be a big deal.
Twelve Labs is an AI platform that empowers developers to create video search and understanding capabilities. Their technology extracts visual, audio, textual and contextual data from videos to enable semantic search, analytics and insights.
How AI learns from video is going to allow for many new emergent capabilities in the future. Search across video content is also hopefully on the internet going to become more ubiquitous and interoperable.
I covered them when they first got funding.
Let’s try to take a look at their new model.
🚀 Introducing Marengo-2.6: A New State-of-the-Art Video Foundation Model for Any-to-Any Search.
Keep reading with a 7-day free trial
Subscribe to Artificial Intelligence Learning 🤖🧠🦾 to keep reading this post and get 7 days of free access to the full post archives.