Xiaoqian Wang (王小倩)
 |
Ron and Dotty Garvin Tonjes Early Career Associate Professor of
Electrical and Computer Engineering 516 Northwestern Ave Email: joywang@purdue.edu |
About Me
My research interests are generally trustworthy machine learning. I am particularly interested in designing novel machine learning models to improve explainability, fairness, and robustness. I also work on the intersection of machine learning and bioinformatics, healthcare. I'm honored to have received the 2022 NSF CAREER award, 2025 Purdue Engineering Outstanding Faculty Mentor Award, and to be recognized as an IEEE senior member.
I obtained my Ph.D. degree from the University of Pittsburgh in 2019, and my advisor is Prof. Heng Huang. Prior to this, I received my bachelor degree from Zhejiang University in 2013.
I am always looking for highly self-motivated Ph.D. students to work on emerging challenges in Machine Learning and/or Healthcare. Please send me your CV and transcripts if you are interested.
Selected Publications
Explainable AI
Rethinking SAE Evaluation: An Atomic Interpretable Unit Framework Reveals Hidden Polysemanticity and Redundancy
Riteng Zhang, and Xiaoqian Wang
In the Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS), 2026.
Accepted to Appear.
Agree to Disagree: Demystifying Homogenenous Deep Ensemble through Output Distributions
Yipei Wang, and Xiaoqian Wang
In the 13th International Conference on Learning Representations (ICLR), 2025.
[Code]
Great Minds Think Alike: The Universal Convergence Trend of Input Salience
Yipei Wang, Jeffrey Mark Siskind, and Xiaoqian Wang
In the Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024.
[Code]
Benchmarking Deletion Metrics with the Principled Explanations
Yipei Wang, and Xiaoqian Wang
In the Forty-First International Conference on Machine Learning (ICML), 2024.
[Code]
Self-Interpretable Model with Transformation Equivariant Interpretation
Yipei Wang, and Xiaoqian Wang
In the Thirty-Fifth Conference on Neural Information Processing Systems (NeurIPS), 2021.
[Code]
Distributional Robustness
Guiding Data Allocation for Robust Subpopulation Generalization
Zhaoying Pan*, Yipei Wang*, Shenyu Lu, and Xiaoqian Wang (* co-first authors)
In the Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS), 2026.
Accepted to Appear.
Think Twice: Test-Time Reasoning for Robust CLIP Zero-Shot Classification
Shenyu Lu, Zhaoying Pan, and Xiaoqian Wang
In the International Conference on Computer Vision (ICCV), 2025.
[Code]
On the Alignment between Fairness and Accuracy: from the Perspective of Adversarial Robustnes
Junyi Chai, Taeuk Jang, Jing Gao, and Xiaoqian Wang
In the Forty-Second International Conference on Machine Learning (ICML), 2025.
[Code]
Identifying and Mitigating Spurious Correlation in Multi-Task Learning
Junyi Chai, Shenyu Lu, and Xiaoqian Wang
In the Forty-Second IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
[Code]
On the Effect of Key Factors in Spurious Correlation: A theoretical Perspective
Yipei Wang, and Xiaoqian Wang
In the Twenty-Seventh International Conference on Artificial Intelligence and Statistics (AISTATS), 2024.
[Code]
Responsible AI
Uncertainty-Aware Hybrid Retrieval for Long-Document RAG
Hoin Jung, and Xiaoqian Wang
In the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2026.
Accepted to Appear.
Rethinking Pareto Frontier: On the Optimal Fairness-Accuracy Trade-off
Junyi Chai, Shenyu Lu, and Xiaoqian Wang
In the International Conference on Learning Representations (ICLR), 2026.
[Code]
SUV: Scalable Large Language Model Copyright Compliance with Regularized Selective Unlearnin
Tianyang Xu*, Xiaoze Liu*, Feijie Wu, Xiaoqian Wang, and Jing Gao (* co-first authors)
In the Second Conference on Language Modeling (COLM), 2025.
[Code]
Target Bias Is All You Need: Zero-Shot Debiasing of Vision-Language Models with Bias Corpus
Taeuk Jang, Hoin Jung, and Xiaoqian Wang
In the International Conference on Computer Vision (ICCV), 2025.
[Code]
A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks
Hoin Jung, Taeuk Jang, and Xiaoqian Wang
In the Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024.
[Code]
Fairness without Demographics through Knowledge Distillation
Junyi Chai, Taeuk Jang, and Xiaoqian Wang
In the Thirty-Sixth Conference on Neural Information Processing Systems (NeurIPS), 2022.
[Code]
Machine Learning in Healthcare and Biomedical Domain
Learning a Continuous Progression Trajectory of Amyloid in Alzheimer’s Disease
Mingzhao Tong, Fahad Mehfooz, Shu Zhang, Yipei Wang, Shiaofen Fang, Andrew J. Saykin, Xiaoqian Wang^, and Jingwen Yan^ (^ co-corresponding authors)
Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring 18 (2026): e70309
Inverse Problem Antidote (IPA): Modeling of Systems Biology Model with Invertible Neural Networks
Linlin Li*, Lu*, David Umulis^, and Xiaoqian Wang^ (* co-first authors, ^ co-corresponding authors)
In the IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2024.
[Code]
Learning the Irreversible Progression Trajectory of Alzheimer's Disease
Yipei Wang, Bing He, Shannon Risacher, Andrew Saykin, Jingwen Yan^, and Xiaoqian Wang^ (^ co-corresponding authors)
In the Twenty-First IEEE International Symposium on Biomedical Imaging (ISBI), 2024.
[Code]
Cumulative Difference Learning VAE for Time-Series with Temporally Correlated Inflow-Outflow
Tianchun Li, Chengxiang Wu, Pengyi Shi, and Xiaoqian Wang
In the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI), 2024.
[Code]