MUMBAI, India, June 24 -- Intellectual Property India has published a patent application (202517039614 A) filed by Google LLC on April 24, 2025, for Systems And Methods For Multi-Reward Reinforcement Learning Framework For Text-To-Image Generation.
Inventors include Lee, Seung Hyun; Yang, Feng; Li, Yinxiao; Ke, Junjie; Yoo, Innfarn; Zhang, Han; Yu, Jiahui; Wang, Qifei; Deng, Fei; Entis, Glenn Michael; He, Junfeng; Li, Gang; and Essa, Irfan Aziz.
The application for the patent was published on June 12, 2026, under issue no. 24/2026.
Abstract: Systems and methods for multi-reward reinforcement learning framework for text-to-image generation are disclosed. The method includes training, in tandem, a prompt expansion model and an image generation model using a multi-reward reinforcement learning model by: processing, by the prompt expansion model, a training query and training context data to generate an expanded training query; generating, by the image generation model, a training set of image data based on the expanded training query; generating a set of reward scores for each image datum within the training set of image data using a set of reward models, wherein generating the set of reward scores comprises generating at least one reward score for each reward criterion within a plurality of reward criteria; and adjusting weights and biases associated with the plurality of reward criteria based on the set of reward scores using the multi-reward reinforcement learning model.
Disclaimer: Curated by HT Syndication.
