Meta on Wednesday announced it’s rolling out a new AI “world model” that can better understand the 3D environment and movements of physical objects.
The tech giant, which owns popular social media apps Facebook and Instagram, said its new open-source AI model V-JEPA 2 can understand, predict and plan in the physical world. Known as a world model, these systems take 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 manner.
For example, in the case of Meta’s new model, V-JEPA 2 can recognize that a ball rolling off a table will fall, or that an object hidden out of view hasn’t just vanished.
Artificial intelligence has been a key focus for Meta CEO Mark Zuckerberg as the company faces competition from players like OpenAI, Microsoft and Google. Meta is set to invest $14 billion into artificial intelligence firm Scale AI and hire its CEO Alexandr Wang to bolster its AI strategy, people familiar with the matter tell CNBC.
Meta touted the benefits of its new V-JEPA 2 model in machines like delivery robots and self-driving cars. These machines need to be able to understand their surroundings in real-time to navigate the physical world.
Rather than relying on large amounts of labelled data or video footage, V-JEPA 2 reasons in a simplified “latent” space to understand how objects move, interact and respond, the tech giant said.
“Allowing machines to understand the physical world is very different from allowing them to understand language,” Yann LeCunn, Meta’s chief AI scientist, said in a video presentation Wednesday at the Viva Tech conference in Paris.
“A world model is like an abstract digital twin of reality that an AI can reference to understand the world and predict consequences of its actions and therefore it would be able to plan a course of action to accomplish a given task,” he added.
The next big thing in AI?
World models have attracted a lot of buzz within the AI community recently as researchers look beyond the large language models behind generative AI apps such as OpenAI’s ChatGPT and Google Gemini.
In September last year, leading AI researcher Fei-Fei Li raised $230 million for a new startup called World Labs, which aims to create what it calls “large world models” that can better understand the structure of the physical world.
Meanwhile, Google’s DeepMind unit has been developing a world model of its own called Genie, which it says can simulate games and 3D environments in real time.
Source: https://www.cnbc.com/
