Listen to the Podcast:
Meta, which is the company that owns Facebook, has made a new artificial intelligence model to make images available to the public.
I-JEPA, Meta’s new “human” model, comes at a time when imagers like Midjourney are making rapid progress in creating photo-like images from scratch, though they often make mistakes, especially with human hands.
Meta says the new I-JEPA model is more accurate than current models because it has better ways to analyze and finish raw images.
At first, the technology is likely to be used primarily by experts and fans of AI imaging. However, this technology is likely to lead to a number of AI-based features being added to Meta platforms like Instagram.
I-JEPA is different from other generative AI models because it doesn’t just use the pixels around it. Instead, it uses “an enormous amount of prior knowledge about the world.”
The AI services that Meta, the Silicon Valley giant that owns Facebook, Instagram and WhatsApp, have so far been limited mostly to an AI technology called LLaMA, which can power robots online.
Mark Zuckerberg, the CEO of Facebook, made a surprising decision in February to make the AI language model available to the public under an open source license. This means that anyone can use the technology behind the model for free. The original code of the new I-JEPA model will also be made public.
The platform is based on the ideas of Yann LeCun, Meta’s chief AI scientist, who wants AI systems to be able to think “like humans.” I-JEPA wants to fix common mistakes in AI-made images by adding this kind of thinking.
“AI researchers have tried to come up with learning algorithms that can take prior common-sense knowledge about the world and turn it into a digital representation that the algorithm can access later,” says Meta.
Notably, this means that unlike older models, the system isn’t set up to see every pixel in an image. Instead, the AI model pays attention to the most important parts.
For example, instead of looking at a pixel-by-pixel image of a person, I-JEPA has been configured to recognize central areas. This allows you to realize that the photo shows a person who should only have five fingers on one hand.
Subscribe to our latest newsletter
To read our exclusive content, sign up now. $5/month, $50/year
Categories: Technology
Source: vtt.edu.vn