This inventor holds 1 USPTO granted patent. Top assignee: Adobe, 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: Yicong Hong and Three-Dimensional Shape Generation
Introduction
Yicong Hong is an inventor based in Canberra, Australia, and is associated with Adobe, Inc. His patent work includes a method for generating three-dimensional shapes from text prompts.
Latest Patents
Hong is named on one patent, titled “Three-dimensional shape generation.” The invention describes a computing system that receives a prompt about a 3D object and uses a latent diffusion model to generate latent features. A hierarchical autoencoder then decodes those features into a 3D shape representation, from which the system produces an output shape. Hong’s listed portfolio includes 1 patent.
Career Highlights
The patent connects Hong’s work with generative modeling and 3D content creation. Its approach combines latent diffusion with hierarchical autoencoding to translate descriptive prompts into three-dimensional shapes.
Collaborations
The patent information provided associates Hong with Adobe, Inc. The described system brings together prompt-based generation, machine-learning models, and 3D shape representation.
Conclusion
Yicong Hong’s patent highlights an approach to generating 3D shapes from text prompts, combining latent diffusion and hierarchical decoding in a system associated with Adobe, Inc.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile