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 at the University of Electronic Science and Technology of China (UESTC), under the supervision of Prof. Ting Zhong and Prof. Fan Zhou. I received my BS degree in Communication Engineering in 2019 and my MS degree in Software Engineering in 2022, advised by Prof. Qiao Liu and Prof. Tian Lan.
My research focuses on controllable generative models and trustworthy artificial intelligence (TAI).
"The soul without imagination is what an observatory would be without a telescope." — Henry Ward Beecher
News
-
[2025-01] Supported by the Youth Talents Support Project -- Doctoral Student Special Program.
-
[2024-12] Paper rebuttal, rejected, revise and resubmit (Ship of Theseus).
-
[2024-01] On a journey to achieve something unique.
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]
Honors
-
Youth Talents Support Project -- Doctoral Student Special Program (China Association for Science and Technology)
2025
-
Academic Rising Star of UESTC
2024
-
Artificial Intelligence Challenge Runner-up (GNN-based Interpretable Community Detection Track), hosted by www.people.com.cn
2023
-
National Scholarship
2023
-
Best Student Paper Award of the 24th IEEE International Conference on Mobile Data Management (MDM)
2023
-
Artificial Intelligence Challenge Runner-up (Dialog Generation Track), hosted by www.people.com.cn
2022
-
Excellent Master's Thesis of UESTC
2022
-
Sichuan Outstanding Graduates
2022
-
National Scholarship
2021
Services
-
Conference Reviewer: ICML, NeurIPS, ICLR, KDD, theWebConf, AISTATS
-
Journal Reviewer: TKDE, TNNLS, TITS, TNSE, TKDD