NvidiaPatent applicationAI & softwareInterest 6/10

Nvidia patents method to mix discrete and continuous AI models for data creation

Patent drawing
Patent drawing from the official filing.

The filing describes a system that uses two types of neural networks to create synthetic data, such as images. One model picks specific categories or features, while the other uses those choices to build the final output.

Why it mattersThis approach could help software developers create more varied and realistic training data for other AI systems without needing real-world examples.

In the filing’s own words

In various examples, systems and methods are disclosed relating to neural networks for synthetic data generation with discrete and continuous variable features. In training, an encoder can determine a plurality of encodings from a plurality of samples of training data, and the continuous generative model can operate as a decoder that is conditioned on the plurality of encodings to generate an estimated output to update the encoder and the continuous generative model. The discrete generative model can be trained over the plurality of encodings to learn to generate discrete variables corresponding to the distribution of information represented by the training data. At runtime, the discrete generative model can be used to generate a discrete variable from an input prompt, and can provide the discrete variable to the continuous generative model for the continuous generative model to generate an output, such an image, conditioned on the discrete variable.

What exactly they claim (claim 1)

1. A processor comprising: one or more circuits to: cause a first generative model to generate, based on an input and a categorical distribution over a plurality of predefined categories, at least one categorical encoding representing at least one discrete class corresponding to one or more features for an output; and cause a second generative model to generate, based on the input, an output conditioned on the at least one categorical encoding.

Facts

Company
Nvidia (NVIDIA Corporation)
Official title
NEURAL NETWORKS FOR SYNTHETIC DATA GENERATION
Publication number
US20260360027A1
Application number
19749224
Filed
Jul 21, 2026
Published
Nov 12, 2026
Inventors
3
Claims
20

Classified under

G06T 11/00 Physics & computingG06F 3/14 Physics & computing

More from Nvidia in AI & software

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.