Whenxuan Wang | Xidian University

👋 About Me

I graduated from the School of Artificial Intelligence in Xidian University and am currently pursuing a master’s degree in the School of Telecommunications Engineering (a member of the State Key Laboratory of Integrated Services Networks).

🔍 Research Interests

My current research interests focus on deep learning based Time Series Analysis (TSA) and Modern Signal Processing. I am passionate about building time series foundation models because I believe time series are external representations of complex dynamical systems, and we are able to distil relevant insights about the real physical world from the models. Subsequently, my research work will gradually transition from traditional TSA to Complex Systems Modeling and Scientific Discovery.

🔥 News

[Sep. 2025] Our paper “SymTime: Synthetic Series-Symbol Data Generation for Time Series Foundation Models” has been accepted by NeurIPS 2025.
[Jun. 2025] My undergraduate thesis was rated as an outstanding thesis of Xidian University.
[May 2024] I have been awarded the Graduate Special Scholarship and Outstanding Graduate Title.
[Oct. 2024] PySDKit: We have developed and open-sourced the first integrated Python library for signal decomposition.
[Sep. 2024] I have been awarded the National Scholarship and School-level Outstanding Student Title.

📃 Publications & Preprints

NeurIPS

Synthetic Series-Symbol Data Generation for Time Series Foundation Models

Wenxuan Wang, Kai Wu#, Yujian Betterest Li, Dan Wang#, Xiaoyu Zhang

Annual Conference on Neural Information Processing Systems, 2025.

PDF Code Poster NeurIPS, CCF A

*Equal Contribution, # Corresponding Author

🔧 Open Source Software

Python

PySDKit: signal decomposition in Python

wwhenxuan, changewam, josefinez, feng1m8

the first integrated Python library for signal decomposition, including EMD, EWT, VMD, STL, etc.

PyPI Code Blog pip install pysdkit

Python

S2Generator: A series-symbol (S2) dual-modality data generation mechanism

wwhenxuan, johnfan12, changewam

A data generation enabling the unrestricted creation of high-quality time series paired with corresponding symbolic representations.

PyPI Code pip install s2generator

💡 Service

ICLR 2026 Reviewer;

🎖️ Honors & Awards

2025 Outstanding Undergraduate Paper (the only one in the major, 60 in the whole school);
2024-2025 Graduate Special Scholarship, Outstanding Graduate Title (First in Major, 1/165);
2023-2024 National Scholarship, School-level Outstanding Student Title;
2023-2024 Xiaomi Scholarship: 5,000 RMB (Only one place available in the school of AI);
2022-2023 First-class Scholarship, School-level Outstanding Student Title;
2022-2023 Song Qingling Future Scholarship: 5,000 RMB;
2021-2022 Third-class Scholarship;