ALEXANDRIA, Va., Dec. 23 -- United States Patent no. 12,505,353, issued on Dec. 23, was assigned to SAMSUNG SDS Co. LTD. (Seoul, South Korea) and SEOUL NATIONAL UNIVERSITY R&DB FOUNDATION (Seoul, South Korea).
"Method and apparatus for training language model for multi-modal dialog" was invented by Hoyoung Kang (Seoul, South Korea), Kyoungwon Park (Seoul, South Korea), Seongho Joe (Seoul, South Korea), Youngjune Gwon (Seoul, South Korea), Gunhee Kim (Seoul, South Korea), Sangho Lee (Seoul, South Korea) and Jaewoo Ahn (Seoul, South Korea).
According to the abstract* released by the U.S. Patent & Trademark Office: "A method for training a language model for multimodal dialog includes generating a first token sequence by tokenizing one or mo...