/Patent Tracker
SamsungPatent applicationAI & softwareInterest 6/10

Samsung patents method to blend AI models for better image-text understanding

Samsung describes a technique for combining multiple artificial intelligence models that understand both images and text. The method mixes specific parts of these models, such as the sections that process images or words, using calculated weights to create a single, more effective model.

Why it mattersThis approach could help tech companies build smarter AI assistants that better understand visual and written context without needing to train entirely new systems from scratch.

In the filing’s own words

A computer-implemented method operated by an electronic device, for generating an improved vision-language model (VLM), includes: obtaining input VLMs including at least one pre-trained based model and a plurality of fined tuned models, wherein each of the at least one pre-trained based model and the plurality of fined tuned models comprises a plurality of components that correspond to a text encoder, a vision encoder, or a projection layer of the VLM; determining a first set of weights that correspond to the plurality of components; generating a first merged model by performing a component-wise merging that comprises: multiplying the plurality of components with the first set of weights; combining the multiplied plurality of components; determining a first performance of the first merged model by validating the first merged model based on an optimization objective.

What exactly they claim (claim 1)

1. A computer-implemented method, operated by an electronic device, for generating an improved vision-language model (VLM), the computer-implemented method comprising: obtaining input VLMs comprising at least one pre-trained based model and a plurality of fined tuned models, wherein each of the at least one pre-trained based model and the plurality of fined tuned models comprises a plurality of components that correspond to a text encoder, a vision encoder, or a projection layer of the VLM; determining a first set of weights that correspond to the plurality of components; generating a first merged model by performing a component-wise merging that comprises: multiplying the plurality of components with the first set of weights; and combining the multiplied plurality of components; determining a first performance of the first merged model by validating the first merged model based on an optimization objective; determining a second set of weights that correspond to the plurality of components; generating a second merged model by performing the component-wise merging using the second set of weights; and determining a second performance of the second merged model by validating the second merged model based on the optimization objective, wherein, in a first case that the first performance exceeds the second performance, the first merged model is used by the electronic device for an application for VLM, and wherein, in a second case that the second performance exceeds the first performance, the second merged model is used by the electronic device for the application for VLM.

Facts

Company
Samsung (SAMSUNG ELECTRONICS CO., LTD.)
Official title
COMPONENT-WISE MERGED VISION-LANGUAGE MODEL
Publication number
US20260268163A1
Application number
19549482
Filed
Feb 25, 2026
Published
Sep 10, 2026
Inventors
3
Claims
18

Classified under

G06N 3/0985 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Samsung 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.