About Me
Welcome to my page! The last time I update this page is June 7th, 2025. This page is still under construction (hence you may notice a lot of different bugs and incomplete stuff) and please come back for more updates!
My name is Daqian Bao, and I am a Ph.D. student in Machine Learning (ML) at the Georgia Institute of Technology (Georgia Tech). From Janurary 2024, I am very fortunate to be able to work with Dr. Justin Romberg as his advisee.
My research is currently on several different fields, a great part of the research is inspired by Dr. Romberg’s previous work on deep learning/compression/compressive sensing:
- The multimodal sensing method for 3D reconstructions.
- For multimodal sensing methods, I am currently working on combining traditional 3D reconstruction algorithms with radar signal processing models to generate 3D rendering in reasonable speed. Although the computation is potentially slower for radar, it is more robust against poor visibility.
- AI for Science. In particular, AI for Digital Signal Processing.
- I am also working on ML models for DSP applications following my advisor’s expertise.
- Spectral properties of optimization algorithms for compression.
- I will provide more update when the time is appropriate.
Prior to starting my Ph.D., I earned my M.S. in Electrical and Computer Engineering from Georgia Tech. During my Master’s degree, I worked on the intersection between ML and partial differential equations (PDE). I had a very pleasant and productive time with Dr. Ali Adibi. The research mainly included:
- AI for Science.
- I used Physics-Informed Neural Networks (PINN) in the design of metasurfaces using Helmholtz’s equation.
I earned my B.S. degrees in Applied Math and Material Science and Engineering from the University of California, Los Angeles (UCLA). I spent two years on the research of semiconductor materials. It was a very fun and intriguing experience.
I am always open to discussing research and potential collaborations. Please feel free to reach out.