Wenxin Tai (台文鑫)

3rd Year PhD Candidate (2022-2026)

ICDM Lab
School of Software Engineering
University of Electronic Science and Technology of China

Email: moc.kooltuo@iatxw
[Google Scholar] [GitHub]

Short Bio

I am currently a PhD candidate in Software Engineering, University of Electronic Science and Technology of China (UESTC), supervised by Prof. Ting Zhong and Prof. Fan Zhou. Before that, I received the BS degree in Communication Engineering and MS degree (supervised by Prof. Qiao Liu and Prof. Tian Lan) in Software Engineering at UESTC in 2019 and 2022, respectively.

The long-term goal of my research is to build a machine that can work well on limited, complex, and uncertain data emerging in real-world applications. To this end, my research focuses on controllable generative probabilistic models and trustworthy artificial intelligence (TAI).

"The soul without imagination is what an observatory would be without a telescope."    ----Henry Ward Beecher

News

[Show more]

Selected Publications

2023

DOSE: Diffusion Dropout with Adaptive Prior for Speech Enhancement
Wenxin Tai, Yue Lei, Fan Zhou*, Goce Trajcevski, Ting Zhong
NeurIPS 2023.
[Paper] [Code]
TrustGeo: Uncertainty-Aware Dynamic Graph Learning for Trustworthy IP Geolocation
Wenxin Tai, Bin Chen, Fan Zhou*, Ting Zhong, Goce Trajcevski, Yong Wang, Kai Chen
KDD 2023.
[Paper] [Code]
Revisiting Denoising Diffusion Probabilistic Models for Speech Enhancement: Condition Collapse, Efficiency and Refinement
Wenxin Tai, Fan Zhou, Goce Trajcevski, Ting Zhong*
AAAI 2023.
[Paper] [Code]
RIPGeo: Robust Street-Level IP Geolocation
Wenxin Tai, Bin Chen, Ting Zhong, Yong Wang, Kai Chen, Fan Zhou*
MDM 2023.
[Paper] [Code]

Honors

Services