Patents by Inventor Abel Salinas

Abel Salinas has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Training methods for language models using data generation and reinforcement learning
    Patent number: 12646507
    Abstract: The disclosed method generates helpful training data for a language model, for example, a model implementing a punctuation restoration task, for real-world ASR texts. The method uses a reinforcement learning method using a generative AI model to generate additional data to train the language model. The method allows the generative AI model to learn from real-world ASR text to generate more effective training examples based on gradient feedback from the language model.
    Type: Grant
    Filed: July 12, 2023
    Date of Patent: June 2, 2026
    Assignee: Adobe Inc.
    Inventors: Viet Dac Lai, Trung Bui, Seunghyun Yoon, Quan Tran, Hao Tan, Hanieh Deilamsalehy, Abel Salinas, Franck Dernoncourt
  • IMPROVED TRAINING METHODS FOR LANGUAGE MODELS USING DATA GENERATION AND REINFORCEMENT LEARNING
    Publication number: 20250022459
    Abstract: The disclosed method generates helpful training data for a language model, for example, a model implementing a punctuation restoration task, for real-world ASR texts. The method uses a reinforcement learning method using a generative AI model to generate additional data to train the language model. The method allows the generative AI model to learn from real-world ASR text to generate more effective training examples based on gradient feedback from the language model.
    Type: Application
    Filed: July 12, 2023
    Publication date: January 16, 2025
    Applicant: Adobe Inc.
    Inventors: Viet Dac Lai, Trung Bui, Seunghyun Yoon, Quan Tran, Hao Tan, Hanieh Deilamsalehy, Abel Salinas, Franck Dernoncourt