The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Oct. 20, 2026

Filed:

Dec. 11, 2025
Applicant:

Gdm Holding Llc, Mountain View, CA (US);

Inventors:

Fabian Julius Mentzer, Zurich, CH;

Kaushik Shivakumar, Cupertino, CA (US);

Robert Junior Riachi, Mountain View, CA (US);

Abhishek Sinha, Mountain View, CA (US);

Xiaoyue Guo, New York, NY (US);

Mostafa Dehghani, Amsterdam, NL;

Assignee:

GDM Holding LLC, Mountain View, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06N 3/04 (2023.01); G06N 3/0455 (2023.01); G06N 3/08 (2023.01);
U.S. Cl.
CPC ...
G06N 3/0455 (2023.01); G06N 3/08 (2013.01);
Abstract

A computer-implemented method of generating multimodal data. The method comprises using a token generation neural network to generate, autoregressively, an output sequence of multimodal tokens. As part of this, a media item, e.g., an image, audio, or video, can be generated conditioned on features of a current output sequence generated by the token generation neural network and an encoded representation of one or more input media items generated by a media encoder neural network.


Find Patent Forward Citations

Mentzer, Fabian. (2026). Generating multimodal data using a media item generation neural network and a token generation neural network (U.S. Patent No. 12769985). U.S. Patent and Trademark Office. https://idiyas.com/patent/badge/12769985

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Loading…