Ph.D. Candidate · Stony Brook University

Dichang
Zhang

I am a Ph.D. candidate in Computer Science at Stony Brook University, advised by Prof. Dimitris Samaras. I also collaborate with Prof. Simon Birrer in the Department of Physics and Astronomy. I have also been a visiting doctoral student at EPFL with Prof. Pascal Fua. Before that, I completed my B.S. in Data Science and Honors Computer Science at the University of Michigan, where I worked with Prof. David Fouhey. I am currently a research intern at Futurewei Technologies.

Research interests: computer vision, machine learning, and astronomy image analysis.

Email CV Google Scholar GitHub
Portrait of Dichang Zhang

Selected Publications

Selected work at the intersection of visual learning and scientific discovery.

Overview of the VLM distillation, sample selection, and test-time prior correction framework

arXiv 2026

A General-Purpose VLM Can Teach an Astronomy Foundation Model to Better Recognize Galaxy Morphology

Dichang Zhang, Jiaqi Deng, Yixuan Shao, Yuanpeng Liu, Jiali Cui, Zhiqiang Lao, Heather Yu, Liang Peng, Simon Birrer, Dimitris Samaras

PaperCode
AS-Bridge framework overview

KDD 2026

AS-Bridge: A Bidirectional Generative Framework Bridging Next-Generation Astronomical Surveys

Dichang Zhang, Yixuan Shao, Simon Birrer, Dimitris Samaras

ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2026

PaperCode
Comparison of HMI Stokes inversion reference and model predictions

The Astrophysical Journal · 2021

Fast and Accurate Emulation of the SDO/HMI Stokes Inversion with Uncertainty Quantification

Richard E. L. Higgins, David F. Fouhey, Dichang Zhang, Spiro K. Antiochos, Graham Barnes, J. Todd Hoeksema, K. D. Leka, Yang Liu, Peter W. Schuck, Tamas I. Gombosi

The Astrophysical Journal, 911(2):130, 2021

PaperCode

Other Publications

Deep Learning-Based Rail Surface Condition Evaluation

Shilin Hu, Ke Ma, Sagnik Das, Dichang Zhang, Dimitris Samaras

International Conference on Computer Vision Workshops, 2025

Adaptive Multitask Neural Network for High-Fidelity Wake Flow Modeling of Wind Farms

Dichang Zhang, Christian Santoni, Zexia Zhang, Dimitris Samaras, Ali Khosronejad

Energies, 2025

Toward Ultra-Efficient High-Fidelity Predictions of Wind Turbine Wakes: Augmenting the Accuracy of Engineering Models via LES-Trained Machine Learning

Christian Santoni, Dichang Zhang, Zexia Zhang, Dimitris Samaras, Fotis Sotiropoulos, Ali Khosronejad

Physics of Fluids, 2024

Transfer Learning in Multi-Fidelity Surrogate Modeling: A Wind Farm Case

Dichang Zhang, Zexia Zhang, Christian Santoni, Ali Khosronejad, Dimitris Samaras

International Conference on Machine Learning Workshops, 2024

Scalable One-Step Synthesis of Hydroxylated Boron Nitride Nanosheets for Obtaining Multifunctional Polyvinyl Alcohol Nanocomposite Films

Wei Cai, Dichang Zhang, Bo Wang, Yuxuan Shi, Ying Pan, Jin Wang, Wen Hu, Yuan Hu

Composites Science and Technology, 2018

Construction of Hierarchical Natural Fabric Surface Structure Based on Two-Dimensional Boron Nitride Nanosheets

Feng Chu, Dichang Zhang, Yifan Hou, Shiyu Qiu, Jin Wang, Wen Hu, Lei Song

ACS Applied Materials & Interfaces, 2018