Xiang Zheng (郑想)

Xiang Zheng received her B.Eng. degree in Artificial Intelligence from the South China University of Technology. She is currently working on improving the efficiency and interpretability of diffusion models at Westlake University.

She was previously a visiting student at UC Berkeley, where she worked as an undergraduate research assistant in Prof. Michael Mahoney's group, under the supervision of Dr. Amir Gholami. Earlier, she interned at the AI for Scientific Simulation and Discovery Lab at Westlake University, mentored by Prof. Tailin Wu. Before that, she conducted research at the Cyber-Med Laboratory, SCUT, under the supervision of Prof. Zhanpeng Jin and Prof. Yang Gao.

Email: xiangzheng@berkeley.edu

Github: https://xiangzheng2002.github.io/

Tel/Wechat: +86-15355021171 / +1-5109848261

Email  /  Twitter  /  Github

profile photo
Research Experience
layoutgpt_gif AI for Scientific Simulation and Discovery Lab, Westlake University
Research Intern   2025/08 – Present
Developing discrete diffusion models with improved efficiency and interpretability.
advised by Prof. Tailin Wu .

layoutgpt_gif Michael Mahoney' Lab, UC Berkeley
undergraduate Research Assistant   2024/09 – 2025/08
Developed foundation models for scientific computing. Built SciML agents that can automatically generate code to solve scientific problems.
advised by Dr. Amir Gholami and Prof. Michael Mahoney.

layoutgpt_gif AI for Scientific Simulation and Discovery Lab, Westlake University
Research Intern   2023/07 – 2024/06
AI for PDE/physical system simulation and control
advised by Prof. Tailin Wu .

layoutgpt_gif Cyber-Med Laboratory, South China University of Technology
Student Research Project Leader   2022/04 – 2023/06
Biometric recognition in Human-Computper Interaction
advised by Prof. ZhanPeng Jin and Prof. Gao Yang.

Education Experience

University of California, Berkeley, Berkeley, United States   08/24 – 05/25(expected)
GPA: 4/4
Main courses:
STAT 154/254 Modern Statistical Prediction and Machine Learning(A+)|  CS 294 Physic-Inspired Machine Learning(A)|  INFO 254 Applied Machine Learning(A)|   CS 194/294 LLM Agent(A)|  CS 194/294 Decentralized Finance(A).

South China University of Technology (SCUT), Guangzhou, China   09/21 – 06/25(expected)
B.Eng   (Majoring in Artificial Intelligence)
GPA: 3.89/4 Rank: 3/80 Main courses:
Machine Learning|   Deep Learning and Computer Vision|   Artificial Intelligence and 3D Vision|   Signal and System|   Calculus I/II| Linear Algebra|   Probability and Statistics|   C++ Programming|   Data Mining   Data Structure &ensp

Contest

Mathematical Contest in Modeling(MCM/ICM), Meritorious Winner
InternationalGenetically Engineered Machine Competition(IGEM), Silver Award
Asia and Pacific Mathematical Contest in Modeling(APMCM), First Prize

Rewards

College Academic Innovation First-Class Scholarship
Hongping Changqing First-Class Scholarship
SCUT Second-Class Scholarship &ensp and so on, for a total of 7 scholarships.

Publication
layoutgpt_gif Wavelet Diffusion Neural Operator

Peiyan Hu *,   Rui Wang *,   Xiang Zheng,   Tao Zhang,   Haodong Feng,   Ruiqi Feng,   Long Wei,   Yue Wang,   Zhi-Ming Ma,   Tailin Wu,  

Wavelet Diffusion Neural Operator (WDNO) is a framework for PDE simulation and control. By modeling trajectories in the wavelet domain and using multi-resolution training, WDNO handles abrupt changes and generalizes across resolutions. It achieves state-of-the-art performance on five physical systems and a real-world dataset (ERA5), significantly improving long-term accuracy and reducing smoke leakage by 78% in a challenging 2D control task.

ICLR 2025

layoutgpt_gif Updating

Author, updating

Updating

IMWUT 2024 2 revision/ 1 reject