Assistant Professor · CSIE, National Taiwan University

Shih-Hsin Wang 王士欣

I work on geometric deep learning, generative models and AI for Science, turning intuition into principled and practical tools.

Choose a path to explore

Google Scholar GitHub LinkedIn CV Email

More about my research

I develop machine learning methods that are both theoretically grounded and practical, spanning geometric deep learning, generative models, and AI for Science. I care about turning intuition into principled, reliable, and efficient tools — and applying them to problems in molecules, biology, and other sciences.

Notes

All notes →

Courses

Diffusion Models and Their Applications From diffusion models and flow matching to discrete generation, one-step models, and guidance at generation time. 7 units · Oct 2026 Geometric Deep Learning Designing machine learning models around the geometric and symmetry structure in data: graph neural networks, invariance and equivariance, and applications to molecules, proteins and other structured data. 6 units · Oct 2026

Foundations

Mathematical Foundations A plain-language introduction to the mathematical tools that recur in machine learning, and to the mathematics the other courses on this site rely on. reused by 67 notes · Oct 2026 Machine Learning Foundations The core concepts, methods and practice of machine learning — the basis for understanding, analyzing and applying different models. reused by 7 notes · Oct 2026

Academic Skills

Recent

Experience →

Aug 2026

Undergraduate project places are full for now; MS/PhD depends on capacity. See Join the Lab for where things stand and how to apply.

Jul 2026

I was named a Yushan Young Fellow by Taiwan's Ministry of Education (Yushan Fellow Program).

Jul 2026

I am organizing two minisymposia on generative models, transport, and inverse problems at SIAM IS26 & MDS26 (Salt Lake City, Nov 2026). [Details]

Jul 2026

I will join the Department of Computer Science and Information Engineering at National Taiwan University as an Assistant Professor in August 2026.

Research

Geometric Deep Learning Equivariant graph neural networks and expressive geometric graph representations.
Generative Models Diffusion models, flow matching, single-step models, and test-time guidance.
AI for Science Modeling complex structures like molecules and proteins.

Selected publications

All publications →

FdAudio: MeanFlow-Anchored Fréchet-Distance Post-Training for One-Step Text-to-Audio Generation

Huang, K. P., Lu, B. R., Chung, H. L., Wang, S. H., Lee, H. Y.

SLT 2026

Test-Time Sequential Steering of Diffusion Models via Preconditioned Crank-Nicolson

Keller, J. A., Transue, T., Li, Q., Wang, S. H., Wang, B.

NeurIPS 2026

Improving the Efficacy of Test-Time Steering in Masked Diffusion Models with Parallel Tempering

Lu, P. Y., Lin, H. T., Wang, S. H.

ICML 2026 GenBio [Spotlight]