avatar

Dong-Dong Wu

Ph.D. Student
The University of Tokyo


About Me

I am a second-year Ph.D. student at the University of Tokyo, where I am fortunate to be supervised by Prof. Masashi Sugiyama. I am also a Junior Research Associate at the Imperfect Information Learning Team, RIKEN Center for Advanced Intelligence Project (RIKEN AIP). Previously, I received my M.Eng. degree from Southeast University under the supervision of Prof. Min-Ling Zhang. I also spent a wonderful time as a Research Assistant at MBZUAI, advised by Prof. Zhiqiang Shen. Earlier in my research journey, I interned at Ant Group and CASIA.

Research Interests

My research focuses mainly on weakly supervised learning (for classification, generation, and LLM post-training), with broader interests in efficient learning (for agents, LLMs, and data) and AI safety. Here’s my CV — feel free to reach me at dongdongwu1230 [at] gmail.com to discuss research.

News

  • Jun. 2026 Received the outstanding Master’s Thesis Award, Jiangsu Computer Society.
  • May 2026 Achieved Rank 1 in AVI Challenge 2026 @ ACM MM 2026.
  • May 2026 One paper accepted at ICML 2026.
  • Mar. 2026 Received the Travel Award for ICLR 2026.
  • Jan. 2026 Two papers accepted at ICLR 2026.

Publications

  1. Positive–Unlabeled Reinforcement Learning Distillation for On-Premise Small Models
    Zhiqiang Kou, Junyang Chen, Xin-Qiang Cai, Xiaobo Xia, Ming-Kun Xie, Dong-Dong Wu, Biao Liu, Yuheng Jia, Xin Geng, Masashi Sugiyama, Tat-Seng Chua
    Proceedings of the 43rd International Conference on Machine Learning (ICML), 2026
    Code
  2. Making Partial-Label Datasets Easier: A Simple Yet Highly Effective Data Augmentation for Deep Partial-Label Learning
    Dong-Dong Wu, Zhaoyi Li, Xiang Li, Zhiqiang Shen
    The 5th DataCV Workshop and Challenge with CVPR2026
    Code
  3. DELTA: Robustly Training Diffusion Models with Weak Annotations
    Dong-Dong Wu, Jiacheng Cui, Wei Wang, Zhiqiang Shen, Masashi Sugiyama
    ICLR 2026 Workshop on Deep Generative Model in Machine Learning: Theory, Principle and Efficacy
    Code
  4. Accessible, Realistic, and Fair Evaluation of Positive-Unlabeled Learning Algorithms
    Wei Wang*, Dong-Dong Wu*, Ming Li, Jingxiong Zhang, Gang Niu, Masashi Sugiyama
    Proceedings of the 14th International Conference on Learning Representations (ICLR), 2026
    Code
  5. A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1
    Zhaoyi Li, Xiaohan Zhao, Dong-Dong Wu, Jiacheng Cui, Zhiqiang Shen
    The 39th Annual Conference on Neural Information Processing Systems (NeurIPS), 2025
    Code Also accepted in ICML 2025 Workshop on Reliable and Responsible Foundation Models
  6. PLENCH: Realistic Evaluation of Deep Partial-Label Learning Algorithms
    Wei Wang, Dong-Dong Wu, Jindong Wang, Gang Niu, Min-Ling Zhang, Masashi Sugiyama
    Proceedings of the 13th International Conference on Learning Representations (ICLR), 2025
    Code Spotlight
  7. Efficient Model Stealing Defense with Noise Transition Matrix
    Dong-Dong Wu, Chilin Fu, Weichang Wu, Wenwen Xia, Xiaolu Zhang, Jun Zhou, Min-Ling Zhang
    Proceedings of the 35th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
    Code
  8. Robust Representation Learning for Unreliable Partial Label Learning
    Yu Shi*, Dong-Dong Wu*, Xin Geng, Min-Ling Zhang
    arXiv preprint, 2024
    Code
  9. Distilling Reliable Knowledge for Instance-dependent Partial Label Learning
    Dong-Dong Wu*, Deng-Bao Wang*, Min-Ling Zhang
    Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI), 2024
    Code
  10. Revisiting consistency regularization for deep partial label learning
    Dong-Dong Wu*, Deng-Bao Wang*, Min-Ling Zhang
    Proceedings of the 39th International Conference on Machine Learning (ICML), 2022
    Code
  11. A new classification method based on the negation of a basic probability assignment in the evidence theory
    Dongdong Wu, Zijing Liu, Yongchuan Tang
    Engineering Applications of Artificial Intelligence (EAAI), 2020, 96: 103985
    Code
  12. A new approach for generation of generalized basic probability assignment in the evidence theory
    Yongchuan Tang, Dongdong Wu, Zijing Liu
    Pattern Analysis and Applications (PAA), 2021, 24(3): 1007-1023
    Code ESI Highly Cited Paper (Top 1%)
  13. An improved failure mode and effects analysis method based on uncertainty measure in the evidence theory
    Dongdong Wu, Yongchuan Tang
    Quality and Reliability Engineering International (QRE), 2020; 36(5): 1786–1807
    Code ESI Highly Cited Paper (Top 1%), Certificate

Experiences

Services

Program Committee Member:

2026(AAAI, PAKDD, AAAI-AIBSD), 2025(IJCAI, ADMA, ECAI)

Conference Reviewer:

2026(ICLR, ICML, CVPR, ECCV, IJCAI, AAAI, AAAI-AIBSD, PAKDD, WACV, BMVC), 2025(ICML, NeurIPS, CVPR, ICCV, IJCAI, ADMA, ECAI), 2024(CVPR, IJCAI, KDD), 2023(ECML-PKDD), 2022(ICML)

Talks

Awards

Competitions:

Honors:

Scholarships:



Powered by Jekyll and Minimal Light theme.