ALEXANDRIA, Va., Sept. 3 -- United States Patent no. 12,405,995, issued on Sept. 2, was assigned to Microsoft Technology Licensing LLC (Redmond, Wash.).
"Using large generative models with improved grounding to improve image context queries" was invented by Vishrav Chaudhary (Covington, Wash.), Bradley Moore Abrams (Palo Alto, Calif.), Kamal Ginotra (Kirkland, Wash.), Owais Khan Mohammed (Bellevue, Wash.), Barun Patra (Vancouver, Canada) and Michael Lawrence Valenzuela (Yelm, Wash.).
According to the abstract* released by the U.S. Patent & Trademark Office: "The disclosure describes utilizing an image query system to improve response accuracy and reduce computational steps resources in responding to natural language queries of input image...