ALEXANDRIA, Va., July 21 -- United States Patent no. 12,688,684, issued on July 21, was assigned to Microsoft Technology Licensing LLC (Redmond, Wash.).

"Training and using a model for content moderation of multimodal media" was invented by Ye Yu (Redmond, Wash.), Gaurav Mittal (Redmond, Wash.), Matthew Brigham Hall (Kenmore, Wash.), Sandra Sajeev (Seattle), Mei Chen (Bellevue, Wash.) and Jialin Yuan (Corvallis, Ore.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A computerized method trains and uses a multimodal fusion transformer (MFT) model for content moderation. Language modality data and vision modality data associated with a multimodal media source is received. Language embeddings are generated from t...