Patents by Inventor Myle Ott

Myle Ott 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).

  • Optimizing key value cache for large language model inference
    Patent number: 12682211
    Abstract: An input sequence is received from a client device. Large language model inference is performed by processing the input sequence through a series of transformer layers to generate one or more tokens including by performing hybrid attention, multi-query attention, and cross-layer key value sharing. The one or more generated tokens are provided to the client device.
    Type: Grant
    Filed: April 28, 2025
    Date of Patent: July 14, 2026
    Assignee: Character Technologies Inc.
    Inventors: Bowen Liang, Noam Mordechai Shazeer, Myle Ott
  • OPTIMIZING KEY VALUE CACHE FOR LARGE LANGUAGE MODEL INFERENCE
    Publication number: 20250390703
    Abstract: An input sequence is received from a client device. Large language model inference is performed by processing the input sequence through a series of transformer layers to generate one or more tokens including by performing hybrid attention, multi-query attention, and cross-layer key value sharing. The one or more generated tokens are provided to the client device.
    Type: Application
    Filed: April 28, 2025
    Publication date: December 25, 2025
    Inventors: Bowen Liang, Noam Mordechai Shazeer, Myle Ott
  • System and methods for automatically detecting deceptive content
    Patent number: 10642975
    Abstract: Systems and methods for detecting deceptive opinion spam. Certain embodiments include a classifier with improved accuracy for detecting deceptive opinion entries. A feature analysis of learned models reveals a relationship between deceptive opinions and imaginative writing. By modeling deception in a generative framework, the prevalence of deception in two popular online review communities may be determined. Deceptive opinion spam is a rapidly growing and widespread problem, especially in review communities with minimal posting requirements.
    Type: Grant
    Filed: October 18, 2012
    Date of Patent: May 5, 2020
    Assignee: Cornell University
    Inventors: Myle Ott, Yejin Choi, Claire Cardie, Jeffrey Hancock
  • SYSTEM AND METHODS FOR AUTOMATICALLY DETECTING DECEPTIVE CONTENT
    Publication number: 20140304814
    Abstract: Systems and methods for detecting deceptive opinion spam. Certain embodiments include a classifier with improved accuracy for detecting deceptive opinion entries. A feature analysis of learned models reveals a relationship between deceptive opinions and imaginative writing. By modeling deception in a generative framework, the prevalence of deception in two popular online review communities may be determined. Deceptive opinion spam is a rapidly growing and widespread problem, especially in review communities with minimal posting requirements.
    Type: Application
    Filed: October 18, 2012
    Publication date: October 9, 2014
    Applicant: Cornell University
    Inventors: Myle Ott, Yejin Chol, Claire Cardie, Jeffrey Hancock