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:
Aug. 11, 2026

Filed:

Mar. 05, 2024
Applicant:

Snap Inc., Santa Monica, CA (US);

Inventors:

Pavlo Chemerys, New York, NY (US);

Colin Eles, Marina del Rey, CA (US);

Ju Hu, Los Angeles, CA (US);

Qing Jin, Palo Alto, CA (US);

Yanyu Li, Quincy, MA (US);

Ergeta Muca, Long Island City, NY (US);

Jian Ren, Marina Del Ray, CA (US);

Dhritiman Sagar, New York, NY (US);

Aleksei Stoliar, Marina del Rey, CA (US);

Sergey Tulyakov, Santa Monica, CA (US);

Huan Wang, Somerville, MA (US);

Assignee:

Snap Inc., Santa Monica, CA (US);

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06V 10/82 (2022.01); G06N 3/0455 (2023.01); G06N 20/00 (2019.01); G06T 5/60 (2024.01); G06T 5/70 (2024.01); G06T 11/00 (2026.01); G10L 15/18 (2013.01); G10L 15/22 (2006.01);
U.S. Cl.
CPC ...
G06V 10/82 (2022.01); G06N 3/0455 (2023.01); G06N 20/00 (2019.01); G06T 5/60 (2024.01); G06T 5/70 (2024.01); G06T 11/00 (2013.01); G10L 15/1815 (2013.01); G10L 15/22 (2013.01); G06T 2200/24 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01);
Abstract

Described is a system for improving machine learning models by accessing a first latent diffusion machine learning model, accessing a second latent diffusion machine learning model that was derived from the first latent diffusion machine learning model, the second latent diffusion machine learning model trained to perform a second number of denoising steps, generating noise data, processing the noise data via the first latent diffusion machine learning model to generate one or more first latent features, processing the noise data via the second latent diffusion machine learning model to generate one or more second latent features, and inputting the one or more first latent features and the one or more second latent features into a loss function. The system then modifies a parameter of the second latent diffusion machine learning model based on the output of the loss function.


Find Patent Forward Citations

Loading…