近年来主要从事深度学习数据优化与可解释性、数据智能与安全的理论算法研究及应用。曾先后就职于中科院自动化所模式识别国家重点实验室、天津大学(国家)应用数学中心等国家级科研机构。曾获中国专利奖、北京科学技术一等奖、北京市发明一等奖，中国电子学会优秀硕士论文指导教师、天津大学教学成果一等奖等奖励。

10/2024-至今             国科大杭州高等研究院智能学院      教授
03/2024-09/2024     香港浸会大学数学系     访问研究员
04/2017-09/2024     天津大学(国家)应用数学中心/数学学院   教授
03/2007-03/2017     中国科学院自动化研究所模式识别国家重点实验室   助理研究员/副研究员

09/2008-01/2012    中国科学院自动化研究所模式识别国家重点实验室  （在职）博士研究生
09/2003-07/2006    中国科学院自动化研究所模式识别国家重点实验室     硕士研究生
09/1999-07/2003    西安交通大学电气工程学院    本科生

围绕“以数据为中心的AI”，开展人工智能数据智能与安全的基本理论、算法与应用研究。

1. 深度学习数据优化与可解释性

    率先探索将机器学习（特别是深度学习）中一大类的面向数据的学习方法与策略（如重采样、增广、扰动、赋权、精简）归纳为一个较为独立的机器学习子分支或者范式：数据优化。我们从理论与实证两个角度对增广、扰动、赋权等算法的核心要素与基本原理进行了研究，并提出了一系列新的深度学习数据优化算法。此外，我们还研究了深度学习组件的可解释性。

2. 面向大模型的数据智能与安全研究

    将侧重以数据为中心的大模型理论与技术的研究。近期主要关注如下几个方面：

    1）面向特定领域的数据合成方法；

    2）大模型价值对齐机理与方法；

    3）大模型演绎+反绎的协同推理方法；

    4）AI数据度量与评测。

    随着AGI进程的不断推进，AI安全将越来越重要，我们主要侧重在其中的数据安全，主要包括:

    1）数据毒化与防范；

    2）合成数据的安全问题以及面向安全的数据合成。

    数据智能与安全将是研究组未来的重心，热诚期待青年学子加入！

3. 文本与图像数据智能分析

    将所研究的深度学习理论与算法用以解决社会与工业应用问题，包括：高并发互联网文本与图像的智能理解、工业控制电路的智能解析、商业智能的视觉解析等。相关技术已经服务于十余家大中型企事业单位。 

欢迎编程基础良好、对人机协同工作模式认同高的优秀青年！

1. 近期拟招募博士后多名，待遇优厚，出站留杭州工作有40~140万的生活/住房补贴、留杭高院工作最高可领180万的生活/住房补贴（具体可点击了解相关详情）；

2. 年度招收博士生（视分配名额情况）、硕士生（每年2名左右）；2025入学的硕士研究生联系名额已满！

3. 今年与我联系的推免生（2026入学），基本都超过了我期望的最低门槛（但我没有参与简历筛选环节）。因此，十月份前暂不确定意向指导关系(恕不一一邮件回复)，如最终选择了杭高院，期盼与我及时联系。

国家、省级以及企业合作项目

2025

1. Yu Zhu, Ou Wu*, Fengguang Su, Subclass-wise Logit Perturbation for Multi-label Learning, ACM Transactions on Knowledge Discovery from Data, 2025.

2. Ou Wu, Rujing Yao*, Data Optimization for Deep Learning: A Survey, IEEE Transactions on Knowledge and Data Engineering, 2025.

3. Rujing Yao, Ou Wu*, Fang Wang, Rethinking Learning Difficulty and Uncertainty of Samples with A Target Perturbation-aware Bias-Variance Decomposition, International Journal of Machine Learning and Cybernetics, 2025.

4. Xiaolin Zhou, Ou Wu*, Nan Yang, Class and Attribute-Aware Logit Adjustment for Generalized Long-Tail Learning, AAAI, 2025.

5. Ou Wu, Data Optimization for LLMs: A Survey, Under review, 2025.

Before 2024

1. Xiaolin Zhou, Ou Wu*, Nan Yang, Adversarial Training with Anti-adversaries, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024.

2. Fengguan Su, Ou Wu*, Weiyao Zhu, Multi-label Adversarial Attack Based on New Measures and Self-paced Weighting, IEEE Transactions on Image Processing, 2024.

3. Weiyao Zhu, Ou Wu*, Nan Yang, IRDA: Implicit data augmentation for deep imbalanced regression, Information Sciences, 2024.

4. Ou Wu*, Mengyang Li，Revisiting the Effective Number Theory for Imbalanced Learning, IEEE Transactions on Knowledge and Data Engineering, 2024.

5. Rujing Yao, Ou Wu*，A Taxonomy for Learning with Perturbation and Algorithms, ACM Transactions on Knowledge Discovery from Data, 2024.

6. Weiyao Zhu, Ou Wu*, Fengguang Su, Yingjun Deng, Exploring the Learning Difficulty of Data: Theory and Measure, ACM Transactions on Knowledge Discovery from Data, 2024.

7. Xiaolin Zhou, Ou Wu*, Mengyang Li，Investigating the Sample Weighting Mechanism Using an Interpretable Weighting Framework, IEEE Transactions on Knowledge and Data Engineering, 2023.

8. Xiaolin Zhou, Ou Wu*，Which Samples Should be Learned First: Easy or Hard? IEEE Transactions on Neural Networks and Learning Systems，2023.

9. Mengyang Li, Fengguang Su, Ou Wu*, Ji Zhang，Class-level Logit Perturbation, IEEE Transactions on Neural Networks and Learning Systems，2023.

10. Xiaolin Zhou, Nan Yang, Ou Wu*，Combining Adversaries with Anti-adversaries in Training, AAAI, 2023.

11. Rujing Yao, Yingchun Ye, Ji Zhang, Shuxiao Li, Ou Wu*, Exploring Developments of the AI Field from the Perspective of Methods, Datasets, and Metrics, Information Processing and Management (IP&M), 2023.

12. Yu Zhu, Yingchun Ye, Mengyang Li, Ji Zhang, Ou Wu*, Investigating Annotation Noise for Named Entity Recognition. Neural Computing Application, 2023. 

13. Ou Wu*, Tao Yang, Mengyang Li, Ming Li，Two-Level LSTM for Sentiment Analysis With Lexicon Embedding and Polar Flipping，IEEE Transactions on Cybernetics，2022.

14. Tao Yang, Qing Yin, Lei Yang, Ou Wu*, Aspect-Based Sentiment Analysis with New Target Representation and Dependency Attention, IEEE Transactions on Affective Computing, 2022.

15. Rujing Yao, Linlin Hou, Lei Yang, Jie Gui, Ou Wu*, Deep human answer understanding for natural reverse QA, Knowledge Based System, 2022.

16. Yu Zhu,  Ou Wu*, Elementary discourse units with sparse attention for multi-label emotion classification, Knowledge Based System, 2022.

17. Xiaoling Zhou,  Ou Wu*, Chao Jiang, Increasing naturalness of human-machine dialogue: The users' choices inference of options in machine-raised questions, Knowledge Based System, 2022.

18. Mengyang Li, Fengguang Su, Ou Wu*，Ji Zhang, Logit Perturbation, AAAI, 2022.

19. Xiaolin Zhou, Ou Wu*, Weiyao Zhu, Ziyang Liang, Understanding Difficulty-Based Sample Weighting with a Universal Difficulty Measure, ECML/PKDD, 2022.

20. Fengguang Su, Yu Zhu, Ou Wu*, Yingjun Deng, Submodular Meta Data Compiling for Meta Optimization, ECML/PKDD, 2022.

21. Rui Wang, Weixuan Xiong, Qing-Hu Hou, Ou Wu*, Tackling the Imbalance for GNNs. IJCNN, 2022,

22. Rui Wang, Shijie Li, Qing Yin, Ji Zhang, Rujing Yao, Ou Wu*, Improved PageRank and New Indices for Academic Impact Evaluation Using AI Papers as Case Studies, Journal of Information Science, 2022.

23. Tao Yang, Rujing Yao, Qing Yin, Qiang Tian, Ou Wu*, Mitigating sentimental bias via a polar attention mechanism. International Journal of Data Science and Analytic, 2021.

24. Pinlong Zhao, Zefeng Han, Qing Yin, Shuxiao Li, Ou Wu*, Sentiment analysis via dually-born-again network and sample selection. Intelligent Data Analysis, 2021.

25. Rui Wang, Xiaoling Zhou, Jian Wu, Ou Wu*, Inter-subdiscipline Analysis Based on Mathematical Statements. JCDL 2020.

26. Pinlong Zhao, Linlin Hou, Ou Wu*, Modeling sentiment dependencies with graph convolutional networks for aspect-level sentiment classification, Knowledge Based System, 2020.

27. Qing Yin, Guan Luo, Xiaodong Zhu, Qinghua Hu, Ou Wu*, Semi-interactive Attention Network for Answer Understanding in Reverse-QA. PAKDD, 2019:

28. Ou Wu*, Mengqiao Han, Screenshot-based color compatibility assessment and transfer for Web pages. Multimedia Tools and Applications, 2018.

29. Ou Wu*, Xue Mao, Weiming Hu, Iteratively Divide-and-Conquer Learning for Nonlinear Classification and Ranking. ACM Transactions on Intelligent System and Technology, 2018.

30. Ou Wu*, Classifier Ensemble by Exploring Supplementary Ordering Information. IEEE Transactions on Knowledge and Data Engineering, 2018.

31. Yunyan Duan, Ou Wu*, Learning With Auxiliary Less-Noisy Labels, IEEE Transactions on Neural Networks and Learning Systems, 2017.

32. Ou Wu*, Qiang You, Fen Xia, Lei Ma, Weiming Hu, Listwise Learning to Rank from Crowds. ACM Transactions on Knowledge Discovery from Data, 2016

33. Ou Wu*, Qiang You, Xue Mao, Fen Xia, Fei Yuan, Weiming Hu, Listwise Learning to Rank by Exploring Structure of Objects, IEEE Transactions on Knowledge and Data Engineering, 2016.

34. Ou Wu*, Haiqiang Zuo, Weiming Hu, Bing Li, Multimodal Web Aesthetics Assessment Based on Structural SVM and Multitask Fusion Learning. IEEE Transactions on Multimedia, 2016

35. Xue Mao, Zhouyu Fu, Ou Wu*, Weiming Hu, Optimizing Locally Linear Classifiers with Supervised Anchor Point Learning. IJCAI 2015

36. Ou Wu, Ruiguang Hu, Xue Mao, Weiming Hu, Quality-Based Learning for Web Data Classification. AAAI 2014

37. Xue Mao, Ou Wu, Weiming Hu, Peter O'Donovan, Nonlinear Classification via Linear SVMs and Multi-Task Learning. CIKM 2014

38. Ou Wu, Shuxiao Li, Honghui Dong, Ying Chen, Weiming Hu, Learning from Multi-User Multi-Attribute Annotations. SDM 2014

39. Ou Wu, Weiming Hu, Lei Shi, Measuring the Visual Complexities of Web Pages. ACM Trans. Web 2013.

40. Ou Wu, Weiming Hu, Stephen J. Maybank, Mingliang Zhu, Bing Li, Efficient Clustering Aggregation Based on Data Fragments. IEEE Trans. Syst. Man Cybern. Part B. 2012

41. Ou Wu, Weiming Hu, Jun Gao, Learning to predict the perceived visual quality of photos. ICCV, 2011.

42. Ou Wu, Weiming Hu, Jun Gao, Learning to Rank under Multiple Annotators. IJCAI, 2011.

43. Ou Wu, Yunfei Chen, Bing Li, Weiming Hu, Evaluating the visual quality of web pages using a computational aesthetic approach. WSDM. 2011

44. Ou Wu, Weiming Hu, Bing Li, Group ranking with application to image retrieval. CIKM, 2010.

45. Ou Wu, Jun Gao, Weiming Hu, Bing Li, Mingliang Zhu, Identifying Multi-instance Outliers. SDM, 2010.

46. Ou Wu, Yunfei Chen, Bing Li, Weiming Hu, Learning to evaluate the visual quality of web pages. WWW, 2010.

1. 国科大杭高院教学委员会委员（2025-）

2. 本科生专业核心课程：数据科学导论（2020-2023）;

2. 本科生选修课程: 深度学习（2021-2023）;