US Patent Issued to QUALCOMM on Aug. 11 for "Efficient diffusion machine learning models" (Dutch, American Inventors)

ALEXANDRIA, Va., Aug. 12 -- United States Patent no. 12,705,708, issued on Aug. 11, was assigned to QUALCOMM Inc. (San Diego).

"Efficient diffusion machine learning models" was invented by Amirhossein Habibian (Amsterdam), Risheek Garrepalli (San Diego) and Fatih Murat Porikli (San Diego).

According to the abstract* released by the U.S. Patent & Trademark Office: "Certain aspects of the present disclosure provide techniques and apparatus for improved machine learning. During a first iteration of processing data using a first denoising backbone of a teacher diffusion machine learning model, a first latent tensor is generated using a lower resolution block of the first denoising backbone. During a first iteration of processing data using a ...