Patents by Inventor Muneeza Azmat

Muneeza Azmat 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).

  • Publication number: 20260288826
    Abstract: According to one embodiment, a method, computer system, and computer program product for improving robustness of a large language model (LLM) is provided. The embodiment may include receiving a set of user prompts to the LLM; generating, via the LLM, a respective associated response to each user prompt; determining a user-approved, associated response to a final user prompt; defining a respective tuple mapping for each user prompt to the user-approved, associated response; generating, via the LLM, an internal prompt representation of the final user prompt using a topic-guided reverse prompt; generating, via the LLM, an associated response to the internal prompt representation; defining respective tuple mappings for the internal prompt representation to the user-approved, associated response and to the associated response; defining a respective tuple mapping for each user prompt to the associated response; and fine-tuning the LLM based on defined tuple mappings.
    Type: Application
    Filed: March 18, 2025
    Publication date: September 24, 2026
    Inventors: Vagner Figueredo de Santana, Rachel Ostrand, Muneeza Azmat
  • Patent number: 12639916
    Abstract: Embodiments are directed to a computer-implemented method of analyzing a land region that has been decomposed into a plurality of regular or irregular sub-regions. The computer-implemented method includes applying, using a processor system, a feature extraction process that extracts a set of sub-region environmental descriptors for each of the plurality of sub-regions. The processor system applies a similarity analysis to the set of sub-region environmental descriptors to generate groups of the plurality of sub-regions. The processor system creates a plurality of group-based graphs by encoding each of the groups into a corresponding group-based graph. A spatio-temporal neural network is used to train a model based at least in part on the plurality of group-based graphs.
    Type: Grant
    Filed: October 4, 2022
    Date of Patent: May 26, 2026
    Assignee: International Business Machines Corporation
    Inventors: Fearghal O'Donncha, Malvern Madondo, Muneeza Azmat, Michael Jacobs, Raya Horesh
  • Publication number: 20240112442
    Abstract: Embodiments are directed to a computer-implemented method of analyzing a land region that has been decomposed into a plurality of regular or irregular sub-regions. The computer-implemented method includes applying, using a processor system, a feature extraction process that extracts a set of sub-region environmental descriptors for each of the plurality of sub-regions. The processor system applies a similarity analysis to the set of sub-region environmental descriptors to generate groups of the plurality of sub-regions. The processor system creates a plurality of group-based graphs by encoding each of the groups into a corresponding group-based graph. A spatio-temporal neural network is used to train a model based at least in part on the plurality of group-based graphs.
    Type: Application
    Filed: October 4, 2022
    Publication date: April 4, 2024
    Inventors: Fearghal O'Donncha, Malvern Madondo, Muneeza Azmat, Michael Jacobs, Raya Horesh