Shih-Hsin Wang

About Me

I'm a third year PhD candidate in Mathematics at the University of Utah. My aim is to unveil profound truths, leveraging math's astonishing might to enrich the world's insights.

As an Applied Mathematician, ...

I aim to understand the underlying principles behind the success of neural networks and reveal insights that can guide future developments and applications of deep learning. Currently, I am primarily concentrating on the domains of Geometric Deep Learning and Diffusion models.

As a Pure Mathematician, ...

I am passionate about studying the theory of singularities in algebraic geometry, with a particular interest in exploring the space of arcs and addressing Nash problems.

As a Mathematician, ...

I also participate in some projects in other fields that require mathematical analysis.


Theoretical Machine Learning

An Explicit Frame Construction for Normalizing 3D Point Clouds
Baker, J.*, Wang, S. H.*, de Fernex, T., Wang, B.,
The Forty-first International Conference on Machine Learning. 2024

Rethinking the Benefits of Steerable Features in 3D Equivariant Graph Neural Networks
Wang, S. H.*, Hsu, Y. C.*, Baker, J., Bertozzi, A. L., Xin, J., & Wang, B.,
The Twelfth International Conference on Learning Representations. 2024

Algebraic Geometry

Families of jets of arc type and higher (co)dimensional Du Val singularities
de Fernex, T., & Wang, S. H.
Comptes Rendus. Mathématique 362.S1 (2024): 119-139.

Other Fields

GenFuzz: GPU-accelerated Hardware Fuzzing using Genetic Algorithm with Multiple Inputs
Lin, D. L., Zhang, Y., Ren, H., Khailany, B., Wang, S. H., & Huang, T. W.
60th ACM/IEEE Design Automation Conference (DAC). IEEE, 2023