This inventor holds 1 USPTO granted patent. Top assignees: International Business Machines Corporation, Rensselaer Polytechnic Institute. Active years: 2026.
Company Filing History:
1 out of 166,209 
1 out of 644 
Years Active: 2026
Title: Qitong Wang: Innovator in Directed Graph Transformers
Introduction
Qitong Wang is a notable inventor based in Troy, NY (US). He has made significant contributions to the field of directed graph transformers, showcasing his innovative approach to technology and data processing. His work has implications for various applications, particularly in machine learning and data analysis.
Latest Patents
Qitong Wang holds a patent for directed graph transformers. This invention involves encoding roles of a node in a directed graph as source and target roles. The patent details a method where source and target query matrices, along with key matrices, are learned based on the directed graph. The attention matrices generated from these encodings are combined to create a source-target vector-edge encoding and a target-source vector-edge encoding. This process is crucial for performing classification tasks based on the generated encodings.
Career Highlights
Throughout his career, Qitong Wang has worked with prominent organizations, including IBM and Rensselaer Polytechnic Institute. His experience in these institutions has allowed him to refine his skills and contribute to groundbreaking research in his field.
Collaborations
One of his notable collaborators is Georgios Kollias. Their partnership has likely fostered innovative ideas and advancements in their respective areas of expertise.
Conclusion
Qitong Wang's contributions to directed graph transformers highlight his role as an influential inventor in the technology sector. His work continues to inspire advancements in data processing and machine learning applications.