ALEXANDRIA, Va., Dec. 31 -- United States Patent no. 12,511,494, issued on Dec. 30, was assigned to Salesforce Inc. (San Francisco).
"Systems and methods for finetuning with learned hidden representations of parameter changes" was invented by Wenzhuo Yang (Singapore), Chu Hong Hoi (Singapore) and Kun Zhang (Hong Kong, Hong Kong).
According to the abstract* released by the U.S. Patent & Trademark Office: "Embodiments described herein provide a parameter-efficient finetuning mechanism, referred to as "factor-tuning," which first learns a compact representation of parameter changes with existing datasets on multiple domains, and then fine-tunes a small number of parameters (automatically extracted from the learned representation) on a new do...