This inventor holds 2 USPTO granted patents. Top assignees: International Business Machines Corporation, Massachusetts Institute of Technology. Active years: 2026.
Company Filing History:


Years Active: 2026
Title: Alexander Gregory Shypula: Innovator in Code Translation
Introduction
Alexander Gregory Shypula is a notable inventor based in East Brunswick, NJ (US). He has made significant contributions to the field of code translation, particularly through his innovative patent. His work focuses on leveraging large language models to create multilingual, low-resource code translation datasets.
Latest Patents
Shypula holds a patent for "Large language models for creating a multi-lingual, low-resource code translation dataset." This patent describes a method where one or more unit-test cases are generated from a monolingual code corpus. The generated unit-test cases are filtered to create a corpus of unit-test cases with acceptability scores exceeding predefined thresholds. The process involves translating code samples from a source language to a target language using a pretrained large language model (LLM). The LLM-translated code samples are then validated using the translated unit-test cases, leading to the creation of a parallel-data training corpus. The pretrained LLM is fine-tuned using this corpus, allowing for the translation and testing of given code segments before deployment.
Career Highlights
Throughout his career, Shypula has worked with prestigious organizations, including IBM and the Massachusetts Institute of Technology. His experience in these institutions has contributed to his expertise in the field of technology and innovation.
Collaborations
Shypula has collaborated with talented individuals such as Zilu Tang and Mayank Agarwal. These partnerships have likely enriched his work and expanded the impact of his inventions.
Conclusion
Alexander Gregory Shypula is a distinguished inventor whose work in code translation through large language models showcases his innovative spirit. His contributions are paving the way for advancements in multilingual programming solutions.