This inventor holds 1 USPTO granted patent and 3 published patent applications. Top assignees: Korea Advanced Institute of Science and Technology, Soongsil University. Active years: 2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
1 out of 2,795 
1 out of 320 
Years Active: 2026
Title: Kijung Shin and Neural Tensor-Train Compression
Introduction
Kijung Shin is an inventor based in Daejeon, South Korea. His work includes a patent on lossy tensor compression using neural network-based tensor-train decomposition.
Latest Patents
Shin is associated with 1 patent: “Lossy Tensor Compression Method Using Neural Network-Based Tensor-Train Decomposition.” The invention describes a computer system that inputs the mode indices of a target tensor entry into a neural tensor-train decomposition (NTTD) model. The model then obtains tensor-train (TT) cores from those indices to reconstruct the target entry as part of a lossy compression process.
Career Highlights
Shin’s listed institutional affiliations include the Korea Advanced Institute of Science and Technology (KAIST) and Soongsil University.
Collaborations
His listed collaborators include Taehyung Kwon and Jinhong Jung.
Conclusion
Kijung Shin’s patent applies neural tensor-train decomposition to lossy tensor compression, reflecting his work in computational methods for representing and reconstructing tensor data.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile