America’s Next AI Accelerator Constraint: Heat, Power and the End of ‘Just Add GPUs’ (UF HWCE)
UF researchers have developed a hybrid photonic–electronic neural network that performs feature extraction using light, marking a breakthrough designed to overcome the energy and speed limits of traditional AI computing.
Turning Up the Light: Harnessing the Potential of Silicon Carbide in Optomechanical Devices (UF ECE)
UF researchers, in collaboration with Carnegie Mellon University (CMU), have developed a chip-sized device that uses forces exerted by photons to “strum” a single-crystal 4H silicon carbide (SiC) microdisk, causing it to vibrate at detectable frequencies.