US Patent Issued to Robert Bosch on Aug. 11 for "Systems and methods for contrastive fine-tuning of image-text machine learning models" (Pennsylvania Inventors)

ALEXANDRIA, Va., Aug. 12 -- United States Patent no. 12,705,872, issued on Aug. 11, was assigned to Robert Bosch GmbH (Germany).

"Systems and methods for contrastive fine-tuning of image-text machine learning models" was invented by Ivan Batalov (Pittsburgh), Chaithanya Kumar Mummadi (Pittsburgh) and Wan-Yi Lin (Wexford, Pa.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method for fine tuning a pre-trained machine learning model includes receiving, from a pre-trained machine learning model, at least one image embedding corresponding to first training data used to train the pre-trained machine learning model. The method also includes receiving, from the pre-trained machine learning model, at least one text...