Qizhou WangPostdoctoral Researcher
Imperfect Information Learning Team,
E-mail: qzwang.ml [at] gmail.com |
I achieved my PhD degree from the Department of Computer Science, Hong Kong Baptist University, advised by Prof. Bo Han. I will soon join the Imperfect Information Learning Team at RIKEN AIP as a postdoctoral researcher, led by Prof. Masashi Sugiyama. I work closely with Dr. Gang Niu, Prof. Tongliang Liu, Prof. Feng Liu, and Dr. Jianing Zhu. I am now interested in LLM post-training, agent, AI safety, and data curation.
@article{yue2025what,
title={What Is Preference Optimization Doing, How and Why?},
author={Wang, Yue and Wang, Qizhou and Zhang, Zizhuo and Li, Ang and Niu, Gang and Han, Bo and Sugiyama, Masashi},
journal = {Arxiv Preprint},
year={2025}
}
@inproceedings{li2026llm,
title={LLM Unlearning with LLM Beliefs},
author={Li, Kemou and Wang, Qizhou and Wang, Yue and Li, Fengpeng and Liu, Jun and Han, Bo and Zhou, Jiantao},
booktitle={International Conference on Learning Representations},
year={2026}
}
@inproceedings{zhang2026towards,
title={Towards Understanding Valuable Preference Data for Large Language Model Alignment},
author={Zhang, Zizhuo and Wang, Qizhou and Ye, Shanshan and Zhu, Jianing and Yao, Jiangchao and Han, Bo and Sugiyama, Masashi},
booktitle={International Conference on Learning Representations},
year={2026}
}
@inproceedings{li2026AEGIS,
title={AEGIS: Adversarial Target–Guided Retention-Data-Free Robust Concept Erasure from Diffusion Models},
author={Li, Fengpeng and Li, Kemou and Wang, Qizhou and Han, Bo and Zhou, Jiantao},
booktitle={International Conference on Learning Representations},
year={2026}
}
@article{chen2026eepo,
inproceedings={EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget},
author={Liang Chen and Xueting Han and Qizhou Wang and Bo Han and Jing Bai and Hinrich Schutze and Kam-Fai Wong},
booktitle={International Conference on Learning Representations},
year={2026}
}
@inproceedings{liao2026explainable,
title={Explainable LLM Unlearning through Reasoning},
author={Liao, Junfeng and Wang, Qizhou and Ye, Shanshan and Yu, Xin and Chen, Ling and Fang, Zhen},
booktitle={International Conference on Learning Representations},
year={2026}
}
@inproceedings{wuerkaixi2025adaptive,
title={Adaptive Localization of Knowledge Negation for Continual LLM Unlearning},
author={Wuerkaixi, Abudukelimu and Wang, Qizhou and Cui, Sen and Xu, Wutong and Han, Bo and Niu, Gang and Sugiyama, Masashi and Zhang, Changshui},
booktitle = {International Conference on Machine Learning},
year={2025}
}
@inproceedings{yang2025exploring,
title={Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning},
author={Yang, Puning and Wang, Qizhou and Huang, Zhuo and Liu, Tongliang and Zhang, Chengqi and Han, Bo},
booktitle = {International Conference on Machine Learning},
year={2025}
}
@inproceedings{wang2025gru,
title={GRU: Mitigating the Trade-off between Unlearning and Retention for Large Language Models},
author={Wang, Yue and Wang, Qizhou and Liu, Feng and Huang, Wei and Du, Yali and Du, Xiaojiang and Han, Bo},
booktitle = {International Conference on Machine Learning},
year={2025}
}
@inproceedings{wang2025rethinking,
title={Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond},
author={Qizhou Wang and Jin Peng Zhou and Zhanke Zhou and Saebyeol Shin and Bo Han and Kilian Q Weinberger},
booktitle = {International Conference on Learning Representations},
year = {2025}
}
@inproceedings{wang2025towards,
title={Towards Effective Evaluations and Comparison for LLM Unlearning Methods},
author={Qizhou Wang and Bo Han and Puning Yang and Jianing Zhu and Tongliang Liu and Masashi Sugiyama},
booktitle = {International Conference on Learning Representations},
year = {2025}
}
@inproceedings{wang2024clip,
title={A Sober Look at the Robustness of CLIPs to Spurious Features},
author={Qizhou Wang and Yong Lin and Yongqiang Chen and Ludwig Schmidt and Bo Han and Tong Zhang},
booktitle={Advances in Neural Information Processing Systems},
year={2024},
}
@inproceedings{wang2023learning,
title={Learning to Augment Distributions for Out-of-distribution Detection},
author={Qizhou Wang and Zhen Fang and Yonggang Zhang and Feng Liu and Yixuan Li and Bo Han},
booktitle={Advances in Neural Information Processing Systems},
year={2023},
}
@inproceedings{zheng2023unreliable,
title={Out-of-distribution Detection with Unreliable Out-of-distribution Sources},
author={Haotian Zheng and Qizhou Wang and Zhen Fang and Xiaobo Xia and Feng Liu and Tongliang Liu and Bo Han},
booktitle={Advances in Neural Information Processing Systems},
year={2023},
}
@inproceedings{wang2023doe,
title={Out-of-distribution Detection with Implicit Outlier Transformation},
author={Qizhou Wang and Junjie Ye and Feng Liu and Quanyu Dai and Marcus Kalander and Tongliang Liu and Jianye Hao and Bo Han},
booktitle = {International Conference on Learning Representations},
year = {2023}
}
@inproceedings{wang2022watermark,
title={Watermarking for Out-of-distribution Detection},
author={Qizhou Wang and Feng Liu and Yonggang Zhang and Jing Zhang and Chen Gong and Tongliang Liu and Bo Han},
booktitle={Advances in Neural Information Processing Systems},
year={2022},
}
@inproceedings{wang2021mail,
title={Probabilistic Margins for Instance Reweighting in Adversarial Training},
author={Qizhou Wang and Feng Liu and Bo Han and Tongliang Liu and Chen Gong and Gang Niu and Mingyuan Zhou and Masashi Sugiyama},
booktitle={NeurIPS},
year={2021}
}
@inproceedings{wang2021tackling_instance,
title={Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model},
author={Qizhou Wang and Bo Han and Tongliang Liu and Gang Niu and Jian Yang and Chen Gong},
booktitle={AAAI},
year={2021}
}
@article{hu2026on,
title={On the Two Facets to Conquer Wild Out-of-distribution Detection},
author={Zhaohui Hu and Qizhou Wang and Xinwang Liu and Long Lan and Bo Han},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
year={2026},
}
@article{wang2025wdoe,
title={W-DOE: Wasserstein Distribution-agnostic Outlier Exposure},
author={Qizhou Wang and Bo Han and Yang Liu and Chen Gong and Tongliang Liu and Jiming Liu},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
year={2025},
}
@article{li2025rmlpp,
title={RML++: Regroup Median Loss for Combating Label Noise},
author={Li, Fengpeng and Li, Kemou and Wang, Qizhou and Han, Bo and Tian, Jinyu and Zhou, Jiantao},
journal={International Journal of Computer Vision},
year={2025},
}
@article{gong2021instance,
title={Instance-dependent positive and unlabeled learning with labeling bias estimation},
author={Gong, Chen and Wang, Qizhou and Liu, Tongliang and Han, Bo and You, Jane and Yang, Jian and Tao, Dacheng},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
volume={44},
number={8},
pages={4163--4177},
year={2021},
}