Can understand, predict and plan in the physical world: Meta launches new AI model
Today, Meta announced the launch of a new AI-powered “world model” called V-JEPA 2, which can better understand 3D environments and the movements of physical objects.
Today, Meta announced the launch of a new AI-powered “world model” called V-JEPA 2, which can better understand 3D environments and the movements of physical objects.
The tech giant said its new open-source artificial intelligence model, V-JEPA 2, can understand, predict and plan in the physical world, CNBC reports .
Known as world models, these systems draw inspiration from the logic of the physical world to build an internal simulation of reality, allowing AI to learn, plan, and make decisions in a more human-like way.
For example, in the case of the new Meta model, V-JEPA 2 can recognize that a ball rolling off a table will fall, or that an object hidden from view has not simply disappeared.
Meta has been touting the benefits of its new V-JEPA 2 model for machines like delivery robots and self-driving cars, which need to be able to understand their surroundings in real time to navigate the physical world.
Instead of relying on large amounts of labeled data or video footage, V-JEPA 2 reasons in a simplified "hidden" space to understand how objects move, interact and react, the tech giant said.
Meta wants to invest $10 billion in AI startup Scale AI. This will be the tech giant's largest investment
Meta wants to invest $10 billion in AI startup Scale AI. This will be the tech giant's largest investment
Meta connects to nuclear reactor: new deal guarantees energy for AI for 20 years
Meta connects to nuclear reactor: new deal guarantees energy for AI for 20 years
Read the country's main IT news in our Telegram
Read the country's main IT news in our Telegram
