Patents by Inventor Eric Emil Malmi

Eric Emil Malmi 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).

  • Semi-Autoregressive Text Editing
    Publication number: 20260220358
    Abstract: Provided are improved machine learning-based text editing models. Specifically, example implementations include a flexible semi-auto-regressive text-editing approach for generation, designed to derive the maximum benefit from non-auto-regressive text-editing and autoregressive decoding. In contrast to conventional sequence-to-sequence (seq2seq) models, the proposed approach is fast at inference time, while being capable of modeling flexible input-output transformations.
    Type: Application
    Filed: March 20, 2026
    Publication date: July 30, 2026
    Inventors: Jonathan Stephen Mallinson, Aliaksei Severyn, Eric Emil Malmi, Jakub Dominik Adamek
  • Semi-autoregressive text editing
    Patent number: 12626050
    Abstract: Provided are improved machine learning-based text editing models. Specifically, example implementations include a flexible semi-auto-regressive text-editing approach for generation, designed to derive the maximum benefit from non-auto-regressive text-editing and autoregressive decoding. In contrast to conventional sequence-to-sequence (seq2seq) models, the proposed approach is fast at inference time, while being capable of modeling flexible input-output transformations.
    Type: Grant
    Filed: May 23, 2022
    Date of Patent: May 12, 2026
    Assignee: GOOGLE LLC
    Inventors: Jonathan Stephen Mallinson, Aliaksei Severyn, Eric Emil Malmi, Jakub Dominik Adamek
  • Semi-Autoregressive Text Editing
    Publication number: 20230376676
    Abstract: Provided are improved machine learning-based text editing models. Specifically, example implementations include a flexible semi-auto-regressive text-editing approach for generation, designed to derive the maximum benefit from non-auto-regressive text-editing and autoregressive decoding. In contrast to conventional sequence-to-sequence (seq2seq) models, the proposed approach is fast at inference time, while being capable of modeling flexible input-output transformations.
    Type: Application
    Filed: May 23, 2022
    Publication date: November 23, 2023
    Inventors: Jonathan Stephen Mallinson, Aliaksei Severyn, Eric Emil Malmi, Jakub Adamek