This inventor holds 1 USPTO granted patent. Top assignee: Amazon Technologies, Inc.. Active years: 2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2026
Title: Seongjun Yun: Innovator in Entity Representation Systems
Introduction
Seongjun Yun is a notable inventor based in Vancouver, Canada. He has made significant contributions to the field of technology, particularly in the development of systems that utilize large language models for entity representation.
Latest Patents
Yun holds a patent for "Systems for determining representations of entities based on graph data using a language model." This innovative patent describes a method where a large language model (LLM) generates an overall entity representation using input that includes individual representations based on graph data, text data, and image data associated with the entity. The patent emphasizes the use of graph data to represent characteristics of the entity and the relationships between it and other entities. Text and image data are also utilized to create comprehensive representations that feed into the LLM, which is trained to generate an entity representation based on this input.
Career Highlights
Seongjun Yun is currently employed at Amazon Technologies, Inc., where he continues to push the boundaries of technology and innovation. His work focuses on enhancing the capabilities of language models in understanding and representing complex entities.
Collaborations
Yun collaborates with talented individuals such as Houyu Zhang and Alejandro Ricardo Mottini d'Oliveira, contributing to a dynamic and innovative work environment.
Conclusion
Seongjun Yun's contributions to the field of entity representation through his patent and work at Amazon Technologies, Inc. highlight his role as a forward-thinking inventor. His innovative approach to utilizing language models for entity representation is paving the way for advancements in technology.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
