Researchers at the UCLA Samueli School of Engineering have created a technology capable of producing novel images using photonics — employing only a fraction of the energy and computational steps per image compared with an array of current generative AI programs.

This process requires only the initial digital encoding and successive optical decoding step; many current generative AI models typically require hundreds to thousands of iterative steps.

The optical generative models use a physical “key-lock” mechanism, preventing unauthorized reconstruction of generated images and offering security measures for communication, content delivery and foiling counterfeits.

University of Virginia researcher Baoxing Xu’s research group introduces HydroSpread, an innovative fabrication method that uses water as a platform to create delicate films and devices for next-generation robotics and sensing.