Patents by Inventor Bryan EIKEMA

Bryan EIKEMA 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).

  • Sampling from discrete energy-based models with quality/efficiency trade-off
    Patent number: 12468777
    Abstract: A sampling system includes: an energy-based model (EBM) configured to generate non-negative scores of an input having discrete classifications, respectively; and a sampling module configured to: generate a sample from a probability distribution of the EBM using a proposal distribution; set a probability of acceptance of the sample based on a minimum of (a) 1 and (b) an acceptance value determined based on the sample, a score of the sample from the EBM, the proposal distribution, and an upper boundary value; determine a distribution value between 0 and 1 using a uniform distribution; and discard the sample when the distribution value is greater than the probability of acceptance of the sample.
    Type: Grant
    Filed: July 29, 2022
    Date of Patent: November 11, 2025
    Assignee: NAVER CORPORATION
    Inventors: Bryan Eikema, German Kruszewski, Hady Elsahar, Stéphane Clinchant, Marc Dymetman
  • SAMPLING FROM DISCRETE ENERGY-BASED MODELS WITH QUALITY/EFFICIENCY TRADE-OFF
    Publication number: 20240037184
    Abstract: A sampling system includes: an energy-based model (EBM) configured to generate non-negative scores of an input having discrete classifications, respectively; and a sampling module configured to: generate a sample from a probability distribution of the EBM using a proposal distribution; set a probability of acceptance of the sample based on a minimum of (a) 1 and (b) an acceptance value determined based on the sample, a score of the sample from the EBM, the proposal distribution, and an upper boundary value; determine a distribution value between 0 and 1 using a uniform distribution; and discard the sample when the distribution value is greater than the probability of acceptance of the sample.
    Type: Application
    Filed: July 29, 2022
    Publication date: February 1, 2024
    Applicant: NAVER CORPORATION
    Inventors: Bryan EIKEMA, German KRUSZEWSKI, Hady ELSAHAR, Stéphane CLINCHANT, Marc DYMETMAN