Shih-Hsin Wang

I’m a fourth-year PhD candidate in Mathematics at the University of Utah, currently visiting UCLA. My research bridges theory and application, spanning geometric deep learning, generative models (e.g., flow matching & diffusion models), and algebraic geometry. I'm especially passionate about AI for Science—leveraging deep mathematical insight to design practical, high-impact models for molecular and biological applications.

Open to research & data scientist roles in ML, Generative Modeling, and AI for Science (See full CV).

News & Updates

Education

University of Utah, Salt Lake City, UT
Ph.D. Candidate in Mathematics
Advisors: Bao Wang, Tommaso de Fernex
Aug. 2021 – Anticipated May 2026

National Taiwan University, Taipei, Taiwan
Bachelor of Science in Mathematics
Sep. 2016 – Jun. 2020

Publications

Machine Learning

Improving Flow Matching by Aligning Flow Divergence
Wang, S. H.*, Huang, Y.*, Transue, T.*, Feldman, W. M., Zhang, H., Wang, B.
ICML 2025

E(3)-Equivariant Fragment-based Graph Neural Networks for Biomolecules
Wang, S. H., Huang, Y., Transue, T., Baker, J. M., Forstater, J., Strohmer, T., Wang, B.
Under Review

A Theoretically-Principled Sparse, Connected, and Rigid Graph Representation of Molecules
Wang, S. H.*, Huang, Y.*, Baker, J., Sun, Y. E., Tang, Q., Wang, B.
ICLR 2025 [Oral Presentation]
[Slides] [Poster] [Code]

Learning to Control the Smoothness of Graph Convolutional Network Features
Wang, S. H.*, Baker, J.*, Hauck, C. D., Wang, B.
Under Review

An Explicit Frame Construction for Normalizing 3D Point Clouds
Wang, S. H.*, Baker, J.*, de Fernex, T., Wang, B.
ICML 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.
ICLR 2024

Algebraic Geometry

Arcs on Du Val Singularities in Arbitrary Characteristics
Wang, S. H., de Fernex, T.
In Preparation

Families of Jets of Arc Type and Higher (Co)Dimensional Du Val Singularities
Wang, S. H., de Fernex, T.
C.R. Math. Acad. Sci. Paris, Special Volume in Memory of Jean-Pierre Demailly (2024)

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.
ACM/IEEE Design Automation Conference (DAC), 2023

Highlights (See full CV)

Recent Experience

Invited Talks & Presentations

Academic Service