杜云涛，副研究员，2023年6月博士毕业于南京大学计算机科学与技术系，2023年7月-2025年2月就职于北京通用人工智能研究院(BIGAI)，担任研究员，联合培养博士生导师，2025年2月加入山东大学。研究方向包括机器学习、迁移学习，大模型智能体、多模态大模型等，近年来发表论文20余篇，其中以第一作者发表论文10余篇，包括CCF-A/清华A类/JCR 1区4篇，Google scholar总引用700余次，单篇论文最高引用270余次，一篇论文入选paper digest评选的CIKM 2021十大最具影响力论文。参与科技部重点研发计划1项、国家自然基金项目1项。担任ICLR、CVPR、ICCV、ECCV、AAAI、TNNLS、TCYB等国际会议和期刊审稿人。
[Google Scholar]: https://scholar.google.com/citations?user=1ogwTXkAAAAJ&hl=zh-CN
[个人主页]：https://yuntaodu.github.io/
招生信息
● 2026级硕士生(保研学生优先)
● 本科生助研3-4名
课题组与南京大学、北京通用人工智能研究院、之江实验室等多个国际一流科研团队始终保持着密切合作，为组内学生提供良好的国内外交流机会。诚挚邀请对机器学习、大语言智能体、多模态大模型等研究领域感兴趣的本科生加入课题组，有意请发邮件联系yuntaodu@sdu.edu.cn，并附个人简历，非常感谢！
代表性论文：
[1] MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge.
Yuntao Du, Kailin Jiang, Zhi Gao, Chenrui Shi, Zilong Zheng, Siyuan Qi, Qing Li
The Thirteenth International Conference on Learning Representations (ICLR) 2025 [PDF]
[2] Robust Logit Adjustment for Learning with Long-Tailed Noisy Data.
MingCai Chen, Yuntao Du, Wenyu Jiang, Baoming Zhang, Shuai Feng, Yi Xin, Chongjun Wang
The 39th Annual AAAI Conference on Artificial Intelligence (AAAI) 2025 [PDF]
[3] V-PETL Bench: A Unified Visual Parameter-Efficient Transfer Learning Benchmark.
Yi Xin*, Siqi Luo*, Xuyang Liu*, Yuntao Du*, Haodi Zhou, Xinyu Cheng, et al.
The Annual Conference on Neural Information Processing Systems (NeurIPS) 2024 [PDF][WebPage]
[4] VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding.
Yue Fan, Xiaojian Ma, Rujie Wu, Yuntao Du, Jiaqi Li, Zhi Gao, Qing Li
The European Conference on Computer Vision (ECCV) 2024 [PDF][中文报道]
[5] Multi-source Fully Test-Time Adaptation.
Yuntao Du, Siqi Luo, Yi Xin, MingCai Chen, Shuai Feng, Mujie Zhang, Chongjun Wang
The Twelfth International Conference on Learning Representations (PML4LRS workshop @ ICLR ) 2024 [PDF]
[6]CLOVA: A Closed-LOop Visual Assistant with Tool Usage and Update.
Zhi Gao, Yuntao Du, Xintong Zhang, Xiaojian Ma, Wenjuan Han, Song-Chun Zhu, Qing Li
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024 [PDF]
[7]Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation
Yuntao Du, Haiyang Yang, Mingcai Chen, Juan Jiang, Hongtao Luo, and Chongjun Wang.
Machine Learning (MLJ) 2023 [PDF]
[8] DSCR: Dual View based Symmetric Consistency Regularization for Semi-Supervised Domain Adaptation
Yuntao Du, Juan Jiang, Hongtao Luo, Haiyang Yang, Mingcai Chen, and Chongjun Wang.
Transactions on Machine Learning Research (TMLR) 2023 [PDF]
[9] Two Wrongs Don’t Make a Right: Combating Confirmation Bias in Learning with Label Noise
Mingcai Chen, Hao Cheng, Yuntao Du , Ming Xu, Wenyu Jiang, Chongjun Wang
AAAI conference on aitificial intelligence (AAAI) 2023 [PDF]
[10] InCo: Intermediate Prototype Contrast for Unsupervised Domain Adaptation
Yuntao Du*, Hongtao Luo*, Haiyang Yang, Juan Jiang, and Chongjun Wang
European Conference on Machine Learning (ECML-PKDD) 2022 [PDF]
[11] Semi-Supervised Learning with Multi-Head Co-Training
Mingcai Chen, Yuntao Du , Yi zhang, Shuwei Qian, and Chongjun Wang
AAAI conference on aitificial intelligence (AAAI) 2022 [PDF]
[12] AdaRNN: Adaptive Learning and Forecasting of Time Series
Yuntao Du , Jindong Wang, Wenjie Feng, Sinno Pan, Tao Qin, Renjun Xu and Chongjun Wang
International Conference on Information and Knowledge Management (CIKM) 2021 [PDF] [Code](引用超260)
[13] Adversarial Separation Network for Cross-Network Node Classification
Xiaowen Zhang *, Yuntao Du *, Rongbiao Xie and Chongjun Wang (*, euqal contribution)
International Conference on Information and Knowledge Management (CIKM) 2021 [PDF] [Code]
[14] Cross-domain error minimization for unsupervised domain adaptation
Yuntao Du, Yinghao Chen *, Fengli Cui *, Xiaowen Zhang, Chongjun Wang. (*, euqal contribution)
International Conference on Database Systems for Advanced Applications (DASFAA) 2021 [PDF] [Code]
[15] Homogeneous Online Transfer Learning with Online Distribution Discrepancy Minimization
Yuntao Du, Zhiwen Tan, Qian Chen, Yi Zhang, Chongjun Wang.
European Conference on Artificial Intelligence (ECAI) 2020 [PDF] [Code]
