Hi there — I’m Yingwei (Noah) Song, a first-year Ph.D. student in Electrical and Computer Engineering at the University of Arizona, advised by Prof. Huanrui Yang, and a Herbold Fellow. I’m broadly interested in 3D reconstruction, diffusion-based generative models, video synthesis, and efficient learning methods — especially in how to build generative systems that are semantically meaningful and computationally efficient on complex spatial and temporal data.

Alongside my Ph.D., I’m a founding research engineer at a seed-stage stealth AI startup, where I lead early research on a 3D-grounded world model and own most of the engineering, from model research and AI infrastructure to backend, frontend, and product design.

Before that, I interned at Hedra as a research engineer, contributing to Character-3, a 13B diffusion transformer for digital-human video. I also spent time as a research assistant at the Harvard Visual Computing Lab with Prof. Hanspeter Pfister and Dr. Wanhua Li, working on 4D LangSplat, and at the Brown Visual Computing Lab with Prof. James Tompkin on neural rendering and scene decomposition.

I received my M.S. in Computer Science from Brown University in 2025 and my B.S. from the University of Wisconsin–Madison in 2023, double majoring in Computer Science and Data Science with a minor in Math.

Beyond research, I build products as a solo developer, and I’m especially fond of Siamese cats and rabbits.

The best way to reach me is by email at muyin1215@gmail.com, or yingwei@arizona.edu for academic matters.