US Patent Issued to NVIDIA on Sept. 22 for "Vision-language model with an ensemble of experts" (American, British Inventors)

ALEXANDRIA, Va., Sept. 24 -- United States Patent no. 12,743,879, issued on Sept. 22, was assigned to NVIDIA Corp. (Santa Clara, Calif.).

"Vision-language model with an ensemble of experts" was invented by Animashree Anandkumar (Pasadena, Calif.), Linxi Fan (Santa Clara, Calif.), Zhiding Yu (Santa Clara, Calif.), Chaowei Xiao (Tempe, Ariz.) and Shikun Liu (London).

According to the abstract* released by the U.S. Patent & Trademark Office: "A vision-language model learns skills and domain knowledge via distinct and separate task-specific neural networks, referred to as experts. Each expert is independently optimized for a specific task, facilitating the use of domain-specific data and architectures that are not feasible with a single large...