ALEXANDRIA, Va., Aug. 12 -- United States Patent no. 12,387,057, issued on Aug. 12, was assigned to Robert Bosch GmbH (Germany) and Carnegie Mellon University (Pittsburgh).
"System and method for utilizing weak learners on large language models" was invented by Hariharan Manikandan (Pittsburgh), Yiding Jiang (Pittsburgh), Jeremy Kolter (Pittsburgh), Chen Qiu (Sindelfingen, Germany), Wan-Yi Lin (Wexford, Pa.) and Filipe J. Cabrita Condessa (Pittsburgh).
According to the abstract* released by the U.S. Patent & Trademark Office: "A computer-implemented method includes converting tabular data to a text representation, generating metadata associated with the text representation of the tabular data, outputting one or more natural language data ...