Santa Clara, CA, United States of America

Zexi Ye

This inventor holds 1 USPTO granted patent and 1 published patent application. Top assignee: Black Sesame Technologies Inc.. Active years: 2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Zexi Ye. Retrieved from https://idiyas.com/inventor/zexi-ye

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

Calculating rank
USPTO Granted Patents = 1 

Average Co-Inventor Count = 1.0

ph-index = 1


Company Filing History:


Years Active: 2026

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

Title: Zexi Ye and Neural Network Acceleration

Introduction

Zexi Ye is an inventor based in Santa Clara, California. His patent work addresses ways to accelerate neural network processing by organizing computational graphs to better account for hardware constraints.

Latest Patents

Ye is associated with 1 patent, titled “Neural Network Acceleration via Graph Partition.” The method receives a directed acyclic graph (DAG), partitions it into one or more sections, and determines relevant hardware attributes and limitations for a section. It then identifies the largest continuous list of nodes in that section that satisfies the hardware limitations.

Career Highlights

Ye’s listed invention focuses on graph partitioning as a way to align neural network computations with hardware capabilities. He works at Black Sesame Technologies Inc., a company involved in technology development.

Collaborations

Ye’s listed coworker is Ting Zhou. Their names are associated with work on neural network acceleration via graph partitioning.

Conclusion

Zexi Ye’s patent describes a graph-partitioning approach for identifying neural network computations that fit hardware constraints, reflecting his work at Black Sesame Technologies Inc.

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…