Kirkland, WA, United States of America

Bingxuan Liang

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

IDiyas Innovation Intelligence. (2026). Inventor Profile: Bingxuan Liang. Retrieved from https://idiyas.com/inventor/bingxuan-liang-m679pkvm

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


Average Co-Inventor Count = 1.0


Company Filing History:


Years Active: 2026

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

Title: Bingxuan Liang and Generative AI for Product Search

Introduction

Bingxuan Liang is an inventor based in Kirkland, Washington, and works at Adobe, Inc. His patent work includes an invention that applies generative artificial intelligence to product search and discovery.

Latest Patents

Liang is associated with 1 patent: “System, Method, and Non-Transitory Computer-Readable Media Using Generative Artificial Intelligence to Optimize Product Search Queries.” The invention describes methods for obtaining product descriptions and images, then using a multimodal style-classification model to classify products. It stores relationships among products in a knowledge graph, based on their styles and descriptions, and uses a text-to-image diffusion model to generate an image featuring a set of related products.

Career Highlights

Liang’s patent reflects work at the intersection of generative AI, multimodal classification, knowledge graphs, and product search. The disclosed system connects product information and visual styles to help optimize search experiences.

Collaborations

Liang’s listed coworkers include Soumya Unnikrishnan and Michele Saad. The patent describes a system involving multiple technical components, though the provided information does not specify the individual contributions of these coworkers.

Conclusion

Bingxuan Liang’s patent highlights an approach to product discovery that combines generative AI, product relationships, and visual information to support more effective search experiences.

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…