Pasadena, CA, United States of America

Pengkai Zhu


Average Co-Inventor Count = 1.0


Company Filing History:


Years Active: 2025

Loading Chart...
1 patent (USPTO):Explore Patents

Title: Pengkai Zhu: Innovator in Document Analysis Technology

Introduction

Pengkai Zhu is a notable inventor based in Pasadena, CA, who has made significant contributions to the field of document analysis technology. He is currently associated with Amazon Technologies, Inc., where he focuses on developing innovative solutions that enhance information extraction from documents.

Latest Patents

Pengkai Zhu holds a patent titled "Document information extraction using visual question answering and document type specific adapters." This invention utilizes document type specific adapters within a document analysis system to facilitate the extraction of information from document images. The system processes a visual question answering (VQA) prompt, which includes a document image and a user-defined question. It generates tokens based on the document image and question, adjusting the encoding of these tokens using document type specific adapters of a transformer model. This approach allows for effective information extraction tailored to various document types.

Career Highlights

Throughout his career, Pengkai Zhu has demonstrated a commitment to advancing technology in document analysis. His work at Amazon Technologies, Inc. showcases his ability to innovate and address complex challenges in the field. His patent reflects his expertise and dedication to improving user interactions with document images.

Collaborations

Pengkai Zhu collaborates with talented individuals in his field, including his coworker, Peng Tang. Together, they contribute to the development of cutting-edge technologies that enhance document analysis capabilities.

Conclusion

Pengkai Zhu's contributions to document analysis technology through his innovative patent highlight his role as a leading inventor in this domain. His work continues to influence the way information is extracted from documents, paving the way for future advancements in the field.

This text is generated by artificial intelligence and may not be accurate.
Please report any incorrect information to support@idiyas.com
Loading…