J. Ryan Shue

I'm an incoming freshman at Stanford University, and will graduate from Milton Academy this year. I'm involved with AI research, teaching, and industrial and mechanical design.

Email  /  Github  /  CV

profile photo
Research

I'm really excited about AI. I recently spearheaded a project on denoising diffusion models advised by Eric Chan, Gordon Wetzstein, and Jiajun Wu at Stanford (see below). I'll be presenting our paper in Vancouver when it gets published at CVPR (a top AI publication) later this year.

3D Neural Field Generation using Triplane Diffusion
J. Ryan Shue*, Eric Ryan Chan*, Ryan Po*, Zachary Ankner*, Jiajun Wu, Gordon Wetzstein
ArXiv, 2022

By factoring a 3D dataset into axis-aligned triplanes, we can train state-of-the-art 2D diffusion models for 3D generation nearly out-of-the-box. We outperform prior art in 3D generation on three classes of ShapeNet.

Teaching

I started and coach a robotics team in Dorchester, funded by the Latino Stem Alliance, with around 20 members. I also run an afterschool coding and robotics program at the Kenny School in Dorchester, with around 30 members. Over the past few years I've taught classes to over 100 kids from Mattapan and Taipei as well.

Selected Projects

Below are some projects I've started, building on various interests.

The Canopy (2020-present)

The Canopy is a tabletop vertical farm. It uses deep water culture hydroponics and artificial lighting to grow plants indoors. We funded our project on Kickstarter and will finish shipping soon.

Zenger3D (2021)

Zenger3D was a moonshot project to fully automate 3D printers. The most expensive part of 3D printing is the painstaking labor, and we hoped to solve this with new hardware and software. We hoped to make the technology more accessible to the masses, including those looking to use 3D printers for real applications.

Zenger Writer (2021)

Zenger Writer was the Zenger3D (see above) software stack. See the link for technical details.


Thanks to Jon Barron for the website template.