# US 2026/0087596 A1 · Selective adaptation in generative machine learning models for enhancing domain alignment

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0087596 A1
- Document ID: US20260087596A1
- Status: Published application
- Kind: A1
- Application number: 18/897,507
- Filed: 2024-09-26
- Published: 2026-03-26
- Earliest claimed: 2024-09-26
- Assignees: QUALCOMM Incorporated
- Applicants: QUALCOMM Incorporated
- Inventors: Minho PARK; Jungsoo LEE; Sunghyun PARK; Hyojin PARK; Sungha CHOI; Kyu Woong HWANG; Fatih Murat PORIKLI
- Web page: https://patentgrep.com/patent/US20260087596A1

## CPC

- G06T 5/60: using machine learning, e.g. neural networks
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 5/70: Denoising; Smoothing
- G06T 5/73: Deblurring; Sharpening
- G06T 11/60: Creating or editing images; Combining images with text
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Systems and techniques are described herein for fine-tuning a machine learning model. For example, a computing device can determine a plurality of sensitivity scores based on a query to edit a first image. Each respective sensitivity score of the plurality of sensitivity scores can be associated with a respective layer of a plurality of layers of a machine learning model. The computing device can apply an adapter to one or more layers of the plurality of layers that have a respective sensitivity score greater than a sensitivity threshold. The computing device can fine-tune parameters of the one or more layers based on application of the adapter to the one or more layers.

## Claims

### Claim 1

An apparatus for fine-tuning machine learning models, the apparatus comprising:
at least one memory; and
at least one processor coupled to the at least one memory and configured to:
determine a plurality of sensitivity scores based on a query to edit a first image, wherein each respective sensitivity score of the plurality of sensitivity scores is associated with a respective layer of a plurality of layers of a machine learning model;
apply an adapter to one or more layers of the plurality of layers that have a respective sensitivity score greater than a sensitivity threshold; and
fine-tune parameters of the one or more layers based on application of the adapter to the one or more layers.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the at least one processor is configured to:
generate the first image using the machine learning model including a first text caption as input;
add noise to the first image to reconstruct the first image; and
determine the plurality of sensitivity scores based on a gradient associated with a loss function representing differences between:
a noise prediction used to reconstruct the first image from the first text caption; and
a noise prediction used to generate a second image from an augmented version of the first text caption.

### Claim 3 (depends on 2)

The apparatus of claim 2, wherein the first text caption includes a description of the first image.

### Claim 4 (depends on 2)

The apparatus of claim 2, wherein the augmented version of the first text caption includes a second caption, the second caption including the first text caption augmented to include a description of features to be edited in the first image.

### Claim 5 (depends on 2)

The apparatus of claim 2, wherein the augmented version of the first text caption includes a request to edit the first image by changing one or more of an art style of the first image and a perspective view of a scene associated with the first image.

### Claim 6 (depends on 1)

The apparatus of claim 1, wherein the sensitivity threshold is variable based on the plurality of sensitivity scores.

### Claim 7 (depends on 1)

The apparatus of claim 1, wherein the sensitivity threshold is set to a value higher than a preset percentage of the plurality of sensitivity scores.

### Claim 8 (depends on 1)

The apparatus of claim 1, wherein the adapter is a low-ranking adaptation (LoRA) adapter.

### Claim 9 (depends on 8)

The apparatus of claim 8, wherein the LoRA adapter is applied head-wise to the one or more layers that have the respective sensitivity score greater than the sensitivity threshold.

### Claim 10

A method for fine-tuning machine learning models, the method comprising:
determining a plurality of sensitivity scores based on a query to edit a first image, wherein each respective sensitivity score of the plurality of sensitivity scores is associated with a respective layer of a plurality of layers of a machine learning model;
applying an adapter to one or more layers of the plurality of layers that have a respective sensitivity score greater than a sensitivity threshold; and
fine-tuning parameters of the one or more layers based on application of the adapter to the one or more layers.

### Claim 11 (depends on 10)

The method of claim 10, further comprising:
generating the first image using the machine learning model including a first text caption as input;
adding noise to the first image to reconstruct the first image; and
determining the plurality of sensitivity scores based on a gradient associated with a loss function representing differences between:
a noise prediction used to reconstruct the first image from the first text caption; and
a noise prediction used to generate a second image from an augmented version of the first text caption.

### Claim 12 (depends on 11)

The method of claim 11, wherein the first text caption includes a description of the first image.

### Claim 13 (depends on 11)

The method of claim 11, wherein the augmented version of the first text caption includes a second caption, the second caption including the first text caption augmented to include a description of features to be edited in the first image.

### Claim 14 (depends on 11)

The method of claim 11, wherein the augmented version of the first text caption includes a request to edit the first image by changing one or more of an art style of the first image and a perspective view of a scene associated with the first image.

### Claim 15 (depends on 10)

The method of claim 10, wherein the sensitivity threshold is variable based on the plurality of sensitivity scores.

### Claim 16 (depends on 10)

The method of claim 10, wherein the sensitivity threshold is set to a value higher than a preset percentage of the plurality of sensitivity scores.

### Claim 17 (depends on 10)

The method of claim 10, wherein the adapter is a low-ranking adaptation (LoRA) adapter.

### Claim 18 (depends on 17)

The method of claim 17, wherein the LoRA adapter is applied head-wise to the one or more layers that have the respective sensitivity score greater than the sensitivity threshold.

### Claim 19

A non-transitory computer readable medium storing code for fine-tuning machine learning models, the code comprising instructions executable by a processor to:
determine a plurality of sensitivity scores based on a query to edit a first image, wherein each respective sensitivity score of the plurality of sensitivity scores is associated with a respective layer of a plurality of layers of a machine learning model;
apply an adapter to one or more layers of the plurality of layers that have a respective sensitivity score greater than a sensitivity threshold; and
fine-tune parameters of the one or more layers based on application of the adapter to the one or more layers.

### Claim 20 (depends on 19)

The non-transitory computer readable medium of claim 19, wherein the code further comprises instructions executable by the processor to:
generate the first image using the machine learning model including a first text caption as input;
add noise to the first image to reconstruct the first image; and
determine the plurality of sensitivity scores based on a gradient associated with a loss function representing differences between:
a noise prediction used to reconstruct the first image from the first text caption; and
a noise prediction used to generate a second image from an augmented version of the first text caption.
