This inventor holds 1 USPTO granted patent. Top assignee: Google Inc.. 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:
Years Active: 2026
Title: Sihyun Yu - Innovator in Temporal Sequence Generation
Introduction
Sihyun Yu is an inventor based in Seongnam-si, South Korea. He is known for his innovative work in the field of artificial intelligence, particularly in generating temporal sequences using advanced neural network techniques. His contributions aim to enhance the capabilities of data processing and generation.
Latest Patent Applications
Sihyun Yu has filed a patent application titled "GENERATING TEMPORAL SEQUENCES USING DIFFUSION TRANSFORMER NEURAL NETWORKS." This application describes methods, systems, and apparatuses, including computer programs encoded on a computer storage medium, for generating an output temporal sequence of data elements conditioned on an input. The method involves obtaining an input that includes a noise input with a respective latent representation for each segment of the temporal sequence. It further details the process of updating the latent representation for each segment using a latent denoising neural network and generating the output temporal sequence by processing the latent representations.
Conclusion
Sihyun Yu's work represents a significant step forward in the field of artificial intelligence and data generation. His innovative approach to generating temporal sequences has the potential to impact various applications in technology and research.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile