Fine-Tuning a Target Generative Neural Network Using an Improvement Generative Neural Network

← USPTO Patent Applications

FINE-TUNING A TARGET GENERATIVE NEURAL NETWORK USING AN IMPROVEMENT GENERATIVE NEURAL NETWORK

Application US20260099906A1 Kind: A1 Apr 09, 2026

Inventors

Qifei Wang, Ying Fan, Yang Zhao, Deepak Ramachandran, Feng Yang, Rahul Anant Jain

Abstract

Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for training a target generative neural network over a plurality of training iterations. At each iteration, a first data item is generated by processing a conditioning input using the target generative neural network. An improvement generative neural network then processes the first data item and the conditioning input to generate a second, preferred data item. A training example is generated that includes the first and second data items and indicates that the second data item is preferred over the first. The target generative neural network is then trained on this training example. By using this iterative process to dynamically generate preference data, the described techniques improve the performance of the generative neural network beyond the limitations of static, offline datasets without requiring computationally expensive reward models or external human annotation.

CPC Classifications

G06T 5/70 G06N 3/0475 G06T 5/60 G06T 2207/20081

Filing Date

2025-10-03

Application No.

19349179

View original document →