Conference

[C65] 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.

[C64] 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.

[C63] When the Same Coefficients Reach Different Places: Asymmetric Realizability in Transplanting Tokenizers across Large Language Models
Xiaoze Liu, Weichen Yu, Matt Fredrikson, Xiaoqian Wang, and Jing Gao
In the Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS) 2026.
Accepted to Appear.

[C62] 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), main conference.
Accepted to Appear.

[C61] Beyond Chunking: Efficient Global Pooling for Holistic Long Document Representation
Hoin Jung, and Xiaoqian Wang
In the Conference on Empirical Methods in Natural Language Processing (EMNLP 2026), main conference.
Accepted to Appear.

[C60] Assessing the Reliability of Image Quality Metrics and Mitigating Quality Bias in Generative Models
Hoin Jung, Shenyu Lu, De Wang, and Xiaoqian Wang
In the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), findings track, 2026. [Code]

[C59] On the Effects of Adversarial Perturbations on Distribution Robustness
Yipei Wang*, Zhaoying Pan*, and Xiaoqian Wang (* co-first authors)
In the ICLR 2026 Workshop on Principled Design for Trustworthy AI - Interpretability, Robustness, and Safety across Modalities.

[C58] Adaptive Logit Adjustment for Debiasing Multimodal Language Models
Hoin Jung, Junyi Chai, and Xiaoqian Wang
In the International Conference on Learning Representations (ICLR), 2026. [Code]

[C57] 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]

[C56] 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]

[C55] 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]

[C54] 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]

[C53] 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]

[C52] 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]

[C51] 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]

[C50] Mitigating Spurious Correlations in Zero-Shot Multimodal Models
Shenyu Lu, Junyi Chai, and Xiaoqian Wang
In the 13th International Conference on Learning Representations (ICLR), 2025. [Code]

[C49] Adversarial Latent Feature Augmentation for Fairness
Hoin Jung, Junyi Chai, and Xiaoqian Wang
In the 13th International Conference on Learning Representations (ICLR), 2025. [Code]

[C48] Towards On-the-Fly Novel Category Discovery in Dynamic Long-Tailed Distributions
Hoin Jung, and Xiaoqian Wang
In the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025. [Code]

[C47] Inverse Problem Antidote (IPA): Modeling of Systems Biology Model with Invertible Neural Networks
Linlin Li*, Shenyu Lu*, David Umulis^, and Xiaoqian Wang^ (* co-first authors, ^ co-corresponding authors)
In the IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2024. [Code]

[C46] SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation
Xiaoze Liu*, Ting Sun*, Tianyang Xu, Feijie Wu, Cunxiang Wang, Xiaoqian Wang, and Jing Gao (* co-first authors)
In the Nineteenth Conference on Empirical Methods in Natural Language Processing (EMNLP), main conference, 2024. [Code]

[C45] Fairness-Aware Online Positive-Unlabeled Learning
Hoin Jung, and Xiaoqian Wang
In the Nineteenth Conference on Empirical Methods in Natural Language Processing (EMNLP), industrial track, 2024. [Code]

[C44] 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), spotlight, 2024. [Code]

[C43] 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]

[C42] Neural Collapse Inspired Debiased Representation Learning for Min-Max Fairness
Shenyu Lu, Junyi Chai, and Xiaoqian Wang
In the Thirtieth SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2024. [Code]

[C41] Benchmarking Deletion Metrics with the Principled Explanations
Yipei Wang, and Xiaoqian Wang
In the Forty-First International Conference on Machine Learning (ICML), 2024. [Code]

[C40] FADES: Fair Disentanglement with Sensitive Relevance
Taeuk Jang, and Xiaoqian Wang
In the Forty-First IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. [Code]

[C39] Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch
Xidong Wu, Shangqian Gao, Zeyu Zhang, Zhenzhen Li, Runxue Bao, Yanfu Zhang, Xiaoqian Wang, and Heng Huang
In the Forty-First IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. [Code]

[C38] 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]

[C37] Explainable Planar Multiband Antenna Designer with Wasserstein Generative Adversarial Network
Hoin Jung, Vinicius Cabral Do Nascimento, Hongyang Liu, Xiaoqian Wang, Cheng-Kok Koh, and Dan Jiao
In the IEEE International Symposium on Antennas and Propagation and ITNC-USNC-URSI Radio Science Meeting (AP-S/URSI), 2024.

[C36] Debiasing Attention Mechanism in Transformer without Demographics
Shenyu Lu, Yipei Wang, and Xiaoqian Wang
In the Twelfth International Conference on Learning Representations (ICLR), 2024. [Code]

[C35] Achieving Fairness through Separability: A Unified Framework for Fair Representation Learning
Taeuk Jang, Hongchang Gao, Pengyi Shi, and Xiaoqian Wang
In the 27th International Conference on Artificial Intelligence and Statistics (AISTATS), 2024. [Code]

[C34] On the Effect of Key Factors in Spurious Correlation: A theoretical Perspective
Yipei Wang, and Xiaoqian Wang
In the 27th International Conference on Artificial Intelligence and Statistics (AISTATS), 2024. [Code]

[C33] Cumulative Difference Learning VAE for Time-Series with Temporally Correlated Inflow-Outflow
Tianchun Li, Chengxiang Wu, Pengyi Shi, and Xiaoqian Wang
In Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI), 2024. [Code]

[C32] Adversarial Fairness Network
Taeuk Jang, Xiaoqian Wang, and Heng Huang
In Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI), 2024. [Code]

[C31] Difficulty-based Sampling for Debiased Contrastive Representation Learning
Taeuk Jang, and Xiaoqian Wang
In Proceedings of the Fortieth IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. [Code]

[C30] SimFair: A Unified Framework for Fairness-Aware Multi-Label Classification
Tianci Liu, Haoyu Wang, Yaqing Wang, Xiaoqian Wang, Lu Su, and Jing Gao
In Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI), 2023. Distinguished Paper Award.

[C29] Why Not Other Classes?: Towards Class-Contrastive Back-Propagation Explanations
Yipei Wang, and Xiaoqian Wang
In Proceedings of the Thirty-Sixth Conference on Neural Information Processing Systems (NeurIPS), 2022. [Code]

[C28] Self-Supervised Fair Representation Learning without Demographics
Junyi Chai, and Xiaoqian Wang
In Proceedings of the Thirty-Sixth Conference on Neural Information Processing Systems (NeurIPS), 2022. [Code]

[C27] Fairness without Demographics through Knowledge Distillation
Junyi Chai, Taeuk Jang, and Xiaoqian Wang
In Proceedings of the Thirty-Sixth Conference on Neural Information Processing Systems (NeurIPS), 2022. [Code]

[C26] Fairness with Adaptive Weights
Junyi Chai, and Xiaoqian Wang
In Proceedings of the 39th International Conference on Machine Learning (ICML), 2022. [Code]

[C25] Group-Aware Threshold Adaptation for Fair Classification
Taeuk Jang, Pengyi Shi, and Xiaoqian Wang
In Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI), 2022. [Code]
Acceptance rate: 15.0% (1349/9020)

[C24] Self-Interpretable Model with Transformation Equivariant Interpretation
Yipei Wang, and Xiaoqian Wang
In Proceedings of the Thirty-Fifth Conference on Neural Information Processing Systems (NeurIPS), 2021. [Code]

[C23] Constructing a Fair Classifier with Generated Fair Data
Taeuk Jang, Feng Zheng, and Xiaoqian Wang
In Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 2021. [Code]

[C22] Shapley Explanation Networks
Rui Wang, Xiaoqian Wang, and David Inouye
In the Ninth International Conference on Learning Representations (ICLR), 2021. [Code]

[C21] On the Convergence of Stochastic Compositional Gradient Descent Ascent Method
Hongchang Gao, Xiaoqian Wang, Lei Luo, and Xinghua Shi
In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI), 2021.
Acceptance rate: 13.9% (587/4284)

[C20] Multi-Task Learning via Sharing Inexact Low-Rank Subspace
Xiaoqian Wang, and Feiping Nie
In the 46th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021.

[C19] Super-Resolution and Inpainting with Degraded and Upgraded Generative Adversarial Networks
Yawen Huang, Feng Zheng, Junyu Jiang, Danyang Wang, Xiaoqian Wang, and Ling Shao
In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI), 2020.
Acceptance rate: 12.6% (592/4717)

[C18] Balanced Self-Paced Learning for Generative Adversarial Clustering Network
Kamran Ghasedi Dizaji, Xiaoqian Wang, Cheng Deng, and Heng Huang
In Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
Acceptance rate: 5.6% (288/5160), oral presentation

[C17] Semi-Supervised Generative Adversarial Network for Gene Expression Inference
Kamran Ghasedi Dizaji*, Xiaoqian Wang*, and Heng Huang (* co-first authors)
In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2018.
Acceptance rate: 18.4% (181/983), research track

[C16] New Balanced Active Learning Model and Optimization Algorithm
Xiaoqian Wang, Yijun Huang, Ji Liu, and Heng Huang
In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI), 2018.

[C15] Directional Label Rectification in Adaptive Graph
Xiaoqian Wang, and Hao Huang
In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI), 2018.

[C14] Temporal Correlation Structure Learning for MCI Conversion Prediction
Xiaoqian Wang, Weidong Cai, Dinggang Shen, and Heng Huang
In Proceedings of the 21st International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2018.

[C13] Regularized Modal Regression with Applications in Cognitive Impairment Prediction
Xiaoqian Wang*, Hong Chen*, Weidong Cai, Dinggang Shen, and Heng Huang (* co-first authors)
In Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS), 2017.

[C12] Group Sparse Additive Machine
Hong Chen, Xiaoqian Wang, Cheng Deng, and Heng Huang
In Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS), 2017.

[C11] Learning A Structured Optimal Bipartite Graph for Co-Clustering
Feiping Nie, Xiaoqian Wang, Cheng Deng, and Heng Huang
In Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS), 2017.

[C10] Longitudinal Genotype-Phenotype Association Study via Temporal Structure Auto-Learning Predictive Model
Xiaoqian Wang, Jingwen Yan, Xiaohui Yao, Sungeun Kim, Kwangsik Nho, Shannon L. Risacher, Andrew J. Saykin, Li Shen, and Heng Huang
In Proceedings of the 21st Annual International Conference on Research in Computational Molecular Biology (RECOMB), 2017.

[C9] Predicting Interrelated Alzheimer’s Disease Outcomes via New Self-Learned Structured Low-Rank Model
Xiaoqian Wang, Kefei Liu, Jingwen Yan, Shannon L. Risacher, Andrew J. Saykin, Li Shen, and Heng Huang
In Proceedings of the 25th Biennial International Conference on Information Processing in Medical Imaging (IPMI), 2017.

[C8] Multiclass Capped \(p\)-Norm SVM for Robust Classifications
Feiping Nie, Xiaoqian Wang, and Heng Huang
In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI), 2017.

[C7] New Robust Clustering Model for Identifying Cancer Genome Landscapes
Hongchang Gao*, Xiaoqian Wang*, and Heng Huang (* co-first authors)
In Proceedings of the IEEE 16th International Conference on Data Mining (ICDM), 2016.
Acceptance rate: 8.6% (78/904), regular paper

[C6] Structured Doubly Stochastic Matrix for Graph Based Clustering
Xiaoqian Wang, Feiping Nie, and Heng Huang
In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2016.
Acceptance rate: 6.3% (70/1115), oral presentation, research track

[C5] The Constrained Laplacian Rank Algorithm for Graph-Based Clustering
Feiping Nie, Xiaoqian Wang, Michael I. Jordan, and Heng Huang
In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI), 2016.

[C4] Prediction of Memory Impairment with MRI Data: A Longitudinal Study of Alzheimer’s Disease
Xiaoqian Wang, Dinggang Shen, and Heng Huang
In Proceedings of the 19th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2016.

[C3] Discriminative Unsupervised Dimensionality Reduction
Xiaoqian Wang, Yun Liu, Feiping Nie, and Heng Huang
In Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI), 2015.

[C2] Clustering and Projected Clustering via Adaptive Neighbor Assignment
Feiping Nie, Xiaoqian Wang, and Heng Huang
In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2014.
Acceptance rate: 14.6% (151/1036), research track

[C1] New Primal SVM Solver with Linear Computational Cost for Big Data Classifications
Feiping Nie, Yizhen Huang, Xiaoqian Wang, and Heng Huang
In Proceedings of the 31st International Conference on Machine Learning (ICML), 2014.

Publication