Shanghai, China

Shi Yun Liang

This inventor holds 3 USPTO granted patents and 10 published patent applications. Top assignee: International Business Machines Corporation. Active years: 2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Shi Yun Liang. Retrieved from https://idiyas.com/inventor/shi-yun-liang

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

USPTO Granted Patents = 3 

Average Co-Inventor Count = 5.0

ph-index = 1


Company Filing History:


Years Active: 2026

Loading Chart...
3 patents (USPTO):Explore Patents

Title: Innovations by Shi Yun Liang in Video Editing Technology

Introduction

Shi Yun Liang is an innovative inventor based in Shanghai, China. He has made significant contributions to the field of video editing technology. His work focuses on improving the quality and consistency of video content through advanced methods.

Latest Patents

Shi Yun Liang holds 1 patent for his invention titled "Goof repair in movies based on large language models (LLMS)." This method addresses the automatic detection and correction of continuity errors in video scenes. It involves generating a textual representation of visual scenes using image caption technology. The method compares this representation with embedded contextual information of the video. It identifies inconsistencies and proposes alternative text to reconcile these errors using a pre-trained large language model. This innovative approach guides image replacement in scenes with identified inconsistencies.

Career Highlights

Shi Yun Liang is currently associated with International Business Machines Corporation, commonly known as IBM. His work at IBM allows him to explore and develop cutting-edge technologies in video editing and artificial intelligence.

Collaborations

Some of his notable coworkers include Jing Zhang and Yuan Yuan Ding, who contribute to the collaborative environment at IBM.

Conclusion

Shi Yun Liang's innovative patent demonstrates the potential of large language models in enhancing video editing processes. His contributions are paving the way for more efficient and accurate video production techniques.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…