publications

2026

1. CVaR-WGF

   Fine-Tuning Generative Models for Extreme Events via CVaR-Penalized Wasserstein Gradient Flows

   Thejani Gamage, Hyemin Gu, Zhizhen Zhang, Ziyu Chen, Markos A. Katsoulakis, and Luc Rey-Bellet

   2026

   arXiv Code
2. Stable-ResNet

   

   Certifying Residual Architectures from Their Primitives: Growth Exponents and Criticality

   Hyemin Gu, Michael Tyrrell, Tuhin Sahai, and Markos A. Katsoulakis

   2026

   arXiv
3. PROFET

   

   PROFET Predicts Continuous Gene Expression Dynamics from scRNA-seq Data to Elucidate Heterogeneity of Cancer Treatment Responses

   Yu-Chen Cheng, Hyemin Gu, Markos A. Katsoulakis, Franziska Michor, and  others

   Cell Systems, 2026

   bioRxiv DOI Code
4. ISOMORPH

   

   ISOMORPH: A Supply Chain Digital Twin for Simulation, Dataset Generation, and Forecasting Benchmarks

   Zhizhen Zhang, Hyemin Gu, Markos A. Katsoulakis, Tuhin Sahai, and  others

   2026

   arXiv Demo Code

2025

1. Robust-alpha-Div

   Robust Generative Learning with Lipschitz-Regularized α-Divergences Allows Minimal Assumptions on Target Distributions

   Ziyu Chen, Hyemin Gu, Markos A. Katsoulakis, Luc Rey-Bellet, and Wei Zhu

   Information and Inference: A Journal of the IMA, 2025

   arXiv DOI Code

2024

1. W-Proximals

   Combining Wasserstein-1 and Wasserstein-2 proximals: robust manifold learning via well-posed generative flows

   Hyemin Gu, Markos A. Katsoulakis, Luc Rey-Bellet, and Benjamin J. Zhang

   2024

   arXiv Code
2. GPA

   

   Lipschitz-Regularized Gradient Flows and Generative Particle Algorithms for High-Dimensional Scarce Data

   Hyemin Gu, Panagiota Birmpa, Yannis Pantazis, Luc Rey-Bellet, and Markos A. Katsoulakis

   SIAM Journal on Mathematics of Data Science, 2024

   arXiv DOI Code