Dong-Dong Wu | The University of Tokyo

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 explores two complementary questions around imperfect information:

Imperfection as a defect — how can models learn reliably from imperfect supervision? To this end, I work on weakly supervised learning across discriminative classification, generative modeling, and LLM post-training.
Imperfection as a design — how can imperfect signals be deliberately crafted to protect models? This drives my work on AI safety: watermarking, model protection, and robustness.

Here’s my CV — feel free to reach me at dongdongwu1230 [at] gmail.com to discuss research.

News

Sep. 2026 Four papers accepted at NeurIPS 2026.
Jul. 2026 One paper accepted at ACM MM 2026.
Jun. 2026 One paper accepted at ECCV 2026.
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

Rethinking Learning from Label Proportions via Moment Matching

Tianhao Ma, Wei Wang, Yivan Zhang, Dong-Dong Wu, Takashi Ishida, Gang Niu, Masashi Sugiyama

The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS), 2026

Code
Watermarking as a Learned Intrinsic Property of Diffusion Models

Xiang Li, Dong-Dong Wu, Masashi Sugiyama, Lannan Luo, Qiang Zeng

The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS), 2026

Code
DELTA: Robustly Training Label-Conditional Diffusion Models with Weak Annotations

Dong-Dong Wu, Jiacheng Cui, Wei Wang, Zhiqiang Shen, Masashi Sugiyama

The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS), 2026

Code Also accepted in ICLR 2026 Workshop on Deep Generative Model in Machine Learning
DenMark: Robust Semantic Watermarking for Diffusion Language Models

Tianhao Ma, Weihao Xuan, Dong-Dong Wu, Farshid Nooshi, Takashi Ishida, Gang Niu, Naoto Yokoya, Masashi Sugiyama

NeurIPS 2026 Workshop on Diffusion Language Models: Foundations, Efficiency, and Reasoning

Code
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 19th European Conference on Computer Vision (ECCV), 2026

Code Also accepted in The 5th DataCV Workshop and Challenge with CVPR2026
Question-Level Multimodal Fusion for Cognitive Ability Assessment in Asynchronous Video Interviews

Zhiqiang Kou*, Jingcheng Duan*, Dong-Dong Wu*, Hanlin Gu, Jing Guo, Yijie Lin, Di Jiang, Yuheng Jia

Proceedings of the 34th ACM International Conference on Multimedia (ACM MM), 2026

Code Rank 1 Solution for AVI Challenge 2026 (ACM MM 2026) – Track 2: Cognitive Ability Assessment
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
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
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
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
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
Robust Representation Learning for Unreliable Partial Label Learning

Yu Shi*, Dong-Dong Wu*, Xin Geng, Min-Ling Zhang

arXiv preprint, 2024

Code
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
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
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
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%)
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

2026.04 - 2027.03, Research Assistant, JST ASPIRE-MWI, Japan. [Advised by Masashi Sugiyama]
2025.04 - 2027.03, Junior Research Associate, RIKEN AIP, Japan. [Advised by Masashi Sugiyama]
2025.04 - 2026.03, Research Assistant, Beyond AI, Japan. [Advised by Masashi Sugiyama]
2024.09 - 2025.03, Research Assistant, MBZUAI, UAE. [Advised by Zhiqiang Shen]
2023.06 - 2023.10, Research Intern, Ant Group, China. [Collaborated with Chilin Fu and Jun Zhou]
2020.06 - 2021.09, Research Intern, Institute of Automation, Chinese Academy of Science, China.

Services

Program Committee Member:

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

Journal Reviewer:

Frontiers of Computer Science

Conference Reviewer:

2027(ICLR, AAAI, IJCAI, PAKDD, ACML, IJCNN, WACV, WSDM), 2026(ICLR, ICML, NeurIPS, 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

"Conditional Diffusion Model Training Meets Imprecise Supervision", International Workshop on Weakly Supervised Learning, 2025.
"ATEC2023 Competition Review and Sharing", Meituan, 2024.

Awards

Competitions:

Rank 1, AVI Challenge 2026 (ACM MM 2026) – Track 2: Cognitive Ability Assessment, 2026. [Paper]
Rank 1 (1/1901, 1M CNY prize), ATEC2023 – LLM Application and Security, 2024. [Report]
Rank 6, ATEC2023 – AI-Generated News Detection Track, 2024.
Rank 6, CCF BDCI – Conversational RAG Track, 2024. [Code]
Rank 7, 1st LMNL Challenge of IJCAI-ECAI2022 – Image Classification Task, 2022. [Code]
Rank 4, 1st LMNL Challenge of IJCAI-ECAI2022 – Label Noise Detection Task, 2022. [Certificate]
Outstanding Winner, International Interdisciplinary Contest in Modeling (ICM), 2019. [Report]

Honors:

Outstanding Master’s Thesis Award, Jiangsu Computer Society (江苏省计算机学会优秀硕士论文), 2026
Outstanding Master’s Thesis Award of Southeast University (东南大学优秀硕士学术学位论文), 2025
Outstanding Master's Graduate in Southeast University, 2024.
Merit Master's Student Pacesetter in Southeast University, 2023.
Outstanding Undergraduate Graduate in Chongqing University, 2021.
Merit Undergraduate Student in Chongqing city, 2020.

Scholarships:

ICLR Travel Award, 2026
Huawei Scholarship, 2024
Lenovo Research Institute Scholarship, 2023
Huawei Scholarship, 2021