US Patent Issued to SRI International on Sept. 9 for "Instruction-guided visual embeddings and feedback-based learning in large vision-language models" (New Jersey, Pennsylvania Inventors)

ALEXANDRIA, Va., Sept. 10 -- United States Patent no. 12,411,879, issued on Sept. 9, was assigned to SRI International (Menlo Park, Calif.).

"Instruction-guided visual embeddings and feedback-based learning in large vision-language models" was invented by Yangyi Chen (Princeton, N.J.), Karan Sikka (Robbinsville, N.J.), Michael A. Cogswell (Yardley, Pa.) and Ajay Divakaran (Monmouth Junction, N.J.).

According to the abstract* released by the U.S. Patent & Trademark Office: "In an example, a method for fine-tuning a Large Visual Language Model (LVLM) includes providing visual queries, each of the visual queries comprises at least an image and a textual query related to the image; processing, by the LVLM, the visual queries to extract visual...