Yuntao Du 杜云涛

About

I am an Associate Researcher and Master's Supervisor at the Joint SDU–NTU Centre for Artificial Intelligence Research and the School of Software, Shandong University. I received my B.Eng. degree from Northeastern University in 2018 and my Ph.D. degree from Nanjing University in 2023. During my doctoral study, I interned at Microsoft Research Asia. From July 2023 to February 2025, I worked as a Research Scientist at the Beijing Institute for General Artificial Intelligence (BIGAI), where I also served as a joint Ph.D. supervisor. I joined Shandong University in February 2025.

My research focuses on multimodal learning, large multimodal models, LLM agents, and transfer learning. I am particularly interested in multimodal knowledge cognition and evolution, trustworthy and efficient multimodal reasoning, repository-level code agents, multi-agent systems, domain adaptation, and test-time adaptation.

I have published more than 30 papers, including 12 first-author or corresponding-author papers in CCF-A conferences or JCR Q1 journals such as ICML, ICLR, NeurIPS, CVPR, and AAAI. These works include two oral papers and one spotlight paper. My publications have received more than 1,800 Google Scholar citations; three papers have each received more than 250 citations, and AdaRNN has received more than 500 citations and was recognized by Paper Digest as one of the most influential CIKM 2021 papers.

Recruitment

Our group maintains close collaborations with research teams at Nanjing University, LMU Munich, Nanjing University of Posts and Telecommunications, Shanghai Artificial Intelligence Laboratory, and other institutions. Students interested in multimodal learning, large multimodal models, and LLM agents are welcome to email me with a CV. Academic and industrial collaborations are also welcome.

News

• 2026.08 I will serve as an Area Chair for ICLR 2026.
• 2026.07 Two papers were accepted by ACM Multimedia 2026.
• 2026.07 One paper was accepted by WISA 2026.
• 2026.06 One paper was accepted by ECCV 2026.
• 2026.05 Three papers were accepted by IJCV, IEEE Transactions on Evolutionary Computation, and ESWC, respectively.
• 2026.05 Two papers were accepted by ICML 2026.
• 2026.04 Two papers were accepted by ACL 2026 Findings.
• 2026.03 One paper was accepted by IJCNN 2026.
• 2026.02 Two papers were accepted by Information Fusion.
• 2026.02 Two papers were accepted by CVPR 2026 (one main-track and one findings paper).
• 2026.01 Two papers were accepted by ICLR 2026.
• 2025.12 Three student teams won first, second, and third national prizes in the Global Campus AI Algorithm Elite Competition.
• 2025.11 Three papers were accepted by AAAI 2026, including two oral papers.
• 2025.09 RepoMaster was accepted by NeurIPS 2025 as a Spotlight paper.
• 2025.08 One paper was accepted by EMNLP 2025 Findings.
• 2025.05 One paper was accepted by ICML 2025.
• 2025.02 I joined Shandong University as an Associate Researcher at C-FAIR.

Selected Publications

Complete publication list on Google Scholar. * indicates equal contribution; 📧 indicates corresponding author.

1. Can Visual Input Be Compressed? A Visual Input Token Compression Benchmark for Large Multimodal Models. Tianfan Peng, Shijie Dong, Pengzhou Ji, Kailin Jiang, Mingchuan Ma, Yijun Tian, Jinhe Bi, Qian Li, Wei Du, Feng Xiao, Lizhen Cui, Yuntao Du📧.
   ACM Multimedia 2026 (CCF-A)
2. M3MAD-Bench: Multi-Dimensional Evaluation of Multi-Agent Debate Across Domains and Modalities.
   Ao Li, Jinghui Zhang, Luyu Li, Yuxiang Duan, Lang Gao, Mingcai Chen, Weijun Qin, Shaopeng Li, Fengxian Ji, Ning Liu, Lizhen Cui, Xiuying Chen, Yuntao Du📧.
   ACM Multimedia 2026 (CCF-A)
3. Delineating Knowledge Boundaries for Honest Large Vision-Language Models.
   Junru Song, Yimeng Hu, Yijing Chen, Huining Li, Qian Li, Lizhen Cui, Yuntao Du📧.
   ECCV 2026 (CCF-B)
4. Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmark. [PDF]
   Yi Xin, Jianjiang Yang, Siqi Luo, Yuntao Du, Qi Qin, Kangrui Cen, Yangfan He, Zhiwei Zhang, Bin Fu, Xiaokang Yang, Guangtao Zhai, Ming-Hsuan Yang, Xiaohong Liu.
   International Journal of Computer Vision, 2026 (CCF-A)
5. MMKU-Bench: A Multimodal Update Benchmark for Diverse Visual Knowledge.
   Baochen Fu*, Yuntao Du*, Cheng Chang, Baihao Jin, Wenzhi Deng, Muhao Xu, Hongmei Yan, Weiye Song, Yi Wan.
   ICML 2026 (CCF-A)
6. KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls.
   Kailin Jiang, Hongbo Jiang, Ning Jiang, Zhi Gao, Jinhe Bi, Yuchen Ren, Bin Li, Yuntao Du, Lei Liu, Qing Li.
   ICML 2026 (CCF-A)
7. MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models.
   Kailin Jiang*, Ning Jiang*, Yuntao Du, Yuchen Ren, Yuchen Li, Yifan Gao, Jinhe Bi, Yunpu Ma, Bin Li, Lei Liu, Qing Li.
   ACL 2026 Findings (CCF-A)
8. VKG-QA: Visual Knowledge Graph-based Question Answer for Large Multimodal Models.
   Yuntao Du, Yiming Wang, Renshuo Yuan, Jincheng Yue, Yijing Chen, Yue Fan, Bo Zhang, Qian Li, Lizhen Cui.
   CVPR 2026 (CCF-A)
9. When Large Multimodal Models Confront Evolving Knowledge: Challenges and Explorations.
   Kailin Jiang*, Yuntao Du*, Yukai Ding, Yuchen Ren, Ning Jiang, Zhi Gao, Zilong Zheng, Lei Liu, Bin Li, Qing Li.
   ICLR 2026
10. Benchmarking Multimodal Knowledge Conflict for Large Multimodal Models. [Project]
    Yifan Jia, Kailin Jiang, Yuyang Liang, Qihan Ren, Yi Xin, Rui Yang, Fenze Feng, Mingcai Chen, Hengyang Lu, Haozhe Wang, Qian Li, Xiaoye Qu, Dongrui Liu, Yuntao Du📧.
    AAAI 2026 (CCF-A)Oral
11. GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging. [PDF]
    Ziyi Ni, Huacan Wang, Shuo Zhang, Shuo Lu, Ziyang He, Wang You, Zhenheng Tang, Yuntao Du📧, Sen Hu, Bo Li, Chen Hu, Binxing Jiao, Daxin Jiang, Pin Lyu.
    AAAI 2026 (CCF-A)Oral
12. RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving. [PDF]
    Huacan Wang, Ziyi Ni, Shuo Zhang, Shuo Lu, Sen Hu, Ziyang He, Chen Hu, Jiaye Lin, Yifu Guo, Yuntao Du📧, Pin Lyu📧.
    NeurIPS 2025 (CCF-A)Spotlight
13. Test-Time Selective Adaptation for Uni-Modal Distribution Shift in Multi-Modal Data. [PDF]
    Mingcai Chen, Baoming Zhang, Zongbo Han, Wenyu Jiang, Yanmeng Wang, Shuai Feng, Yuntao Du📧, Bingkun Bao📧.
    ICML 2025 (CCF-A, equal corresponding author)
14. MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge. [PDF] [Project]
    Yuntao Du, Kailin Jiang, Zhi Gao, Chenrui Shi, Zilong Zheng, Siyuan Qi, Qing Li.
    ICLR 2025
15. V-PETL Bench: A Unified Visual Parameter-Efficient Transfer Learning Benchmark. [PDF] [Project]
    Yi Xin*, Siqi Luo*, Xuyang Liu*, Yuntao Du*, et al.
    NeurIPS 2024 (CCF-A, equal first author)
16. VideoAgent: A Memory-Augmented Multimodal Agent for Video Understanding. [PDF] [Project]
    Yue Fan, Xiaojian Ma, Rujie Wu, Yuntao Du, Jiaqi Li, Zhi Gao, Qing Li.
    ECCV 2024 (CCF-B)
17. CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Update. [PDF] [Project]
    Zhi Gao, Yuntao Du, Xintong Zhang, Xiaojian Ma, Wenjuan Han, Song-Chun Zhu, Qing Li.
    CVPR 2024 (CCF-A)
18. Multi-Source Fully Test-Time Adaptation. [PDF]
    Yuntao Du, Siqi Luo, Yi Xin, Mingcai Chen, Shuai Feng, Mujie Zhang, Chongjun Wang.
    Neural Networks, 2025 (JCR Q1, CCF-B)
19. Generation, Augmentation, and Alignment: A Pseudo-Source Domain Based Method for Source-Free Domain Adaptation. [PDF]
    Yuntao Du, Haiyang Yang, Mingcai Chen, Juan Jiang, Hongtao Luo, Chongjun Wang.
    Machine Learning, 2024 (JCR Q1, CCF-B)
20. AdaRNN: Adaptive Learning and Forecasting of Time Series. [PDF] [Code]
    Yuntao Du, Jindong Wang, Wenjie Feng, Sinno Pan, Tao Qin, Renjun Xu, Chongjun Wang.
    CIKM 2021 (CCF-B)500+ citations

Research Projects as Principal Investigator

• Mitigating Multimodal Factual Hallucinations under Cognitive Boundary Constraints, Young Scientists Fund of the National Natural Science Foundation of China (Category C), 2027–2029.
• Collaborative Decision-Making and Adaptive Task Planning for Industrial Agents, Shandong Provincial Natural Science Foundation Joint Fund, 2026–2029.
• Multi-Agent Reasoning Systems for Patrol Scenarios, CAAI–Lenovo Blue Sky Research Fund, 2026–2027.
• Efficient Inference for Large Multimodal Models, Shandong Provincial Natural Science Foundation Young Scholars Program, 2025–2028.
• Efficient Inference Algorithms for Large Multimodal Models, Key Laboratory Open Fund, 2025–2027.

Students

Professional Service & Awards

Education & Experience

• 2025.02–present · Associate Researcher, Shandong University.
• 2023.07–2025.02 · Research Scientist, Beijing Institute for General Artificial Intelligence (BIGAI).
• 2020.05–2020.10 · Research Intern, Microsoft Research Asia.
• 2018.09–2023.06 · Ph.D. in Computer Science and Technology, Nanjing University.
• 2014.10–2018.06 · B.Eng. in Computer Science and Technology, Northeastern University.