Mountain View, CA, United States of America

Sirui Bi

This inventor holds 1 USPTO granted patent. Top assignee: Intuit, Inc.. Active years: 2026.


Average Co-Inventor Count = 1.0


Company Filing History:


Years Active: 2026

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

Title: Sirui Bi: Innovator in Large Language Models

Introduction

Sirui Bi is an accomplished inventor based in Mountain View, CA (US). He has made significant contributions to the field of artificial intelligence, particularly in the development of large language models. His innovative approach has led to the creation of a unique patent that enhances the reasoning capabilities of these models.

Latest Patents

Sirui Bi holds a patent titled "Adaptive confidence-based reasoning control for large language models." This method involves transmitting a prompt to a large language model (LLM) that includes an instruction to generate a first reasoning block. The process includes computing a first token-level confidence score for the first reasoning block. If this score does not meet a specified pruning threshold, the LLM generates a second reasoning block. A second token-level confidence score is then computed for this block. If the second score meets the block confidence threshold, the second reasoning block is added to a reasoning trace, ultimately leading to the generation of a provisional answer.

Career Highlights

Sirui Bi is currently employed at Intuit, Inc., where he continues to push the boundaries of technology and innovation. His work focuses on improving the functionality and reliability of large language models, making them more effective for various applications.

Collaborations

One of his notable collaborators is Wei Wang, who is also a talented professional in the field. Together, they work on advancing the capabilities of artificial intelligence technologies.

Conclusion

Sirui Bi's contributions to the field of large language models exemplify the innovative spirit of modern inventors. His patent reflects a significant advancement in AI technology, showcasing his expertise and dedication to improving machine reasoning.

This text is generated by artificial intelligence and may not be accurate.
Please report any incorrect information to [email protected]
Loading…