Meta unveils ‘human-like’ artificial intelligence model for image creation

Meta Platforms said on Tuesday it would give researchers access to the components of a new “human-like” artificial intelligence model that it said could analyze and complete incomplete images more accurately than existing models. Is.

The company said the model, I-JEPA, uses background knowledge about the world to fill in missing pieces of images, rather than just looking at nearby pixels like other generative AI models.

The approach incorporates human-like reasoning championed by Meta’s top AI scientist Yann LeCun and helps the technology avoid errors that are common to AI-generated images, such as hands with extra fingers, Said this.

Meta, which owns Facebook and Instagram, is a prolific publisher of open-source AI research through its in-house research lab. Chief Executive Officer Mark Zuckerberg has said that sharing models developed by Meta’s researchers can help the company drive innovation, narrow security gaps and reduce costs.

“For us, it is better for the industry to standardize the basic tools that we are using and so we can benefit from improvements that others make,” he told investors in April.

Company executives have dismissed warnings from others in the industry about the potential dangers of the technology, refusing to sign a statement endorsed last month by top executives from OpenAI, DeepMind, Microsoft and Google, which called for a response to pandemics and wars. equated its risks with

Lacan, considered one of the “godfathers of AI”, has spoken out against “AI doomsday” and argued in favor of building safety checks into AI systems.

Meta is also starting to incorporate generative AI features into its consumer products, such as advertising tools that can create image backgrounds and an Instagram product that can modify a user’s photos, both based on text prompts.

(This story has not been edited by News18 staff and is published from a syndicated news agency feed – reuters,