I am currently an Associate Professor in the School of Computer Science and Technology at Nanjing University of Posts and Telecommunications. I earned my Ph.D. in Computer Science and Technology from Nanjing University.

My research focuses on deep learning under imperfect data and in open-environments, particularly in areas such as learning with noisy labels and distribution shift. I welcome collaboration and inquiries and am passionate about academic exchange. I look forward to working with scholars and researchers from diverse fields to explore new research directions together.

Selected Publications

Mingcai Chen, Heng-yang Lu, Yuntao Du, Baoming Zhang, and Hao Zhou. Test-Time Adaptation via Self-Reinforced Optimal Transport for Zero-Shot OOD Detection with Vision–Language Models. Proceedings of the 40th Annual Conference on Neural Information Processing Systems (NeurIPS’26). [Acceptance Rate: ~25.7%]

Hao Zhou, SiQi Cai, Hua Dai, Letian Sha, Yichen Li, and Mingcai Chen†. Budget-Conditioned Clipping Policies for Differentially Private Federated Learning. Proceedings of the 40th Annual Conference on Neural Information Processing Systems (NeurIPS’26). [Acceptance Rate: ~25.7%]

Xianjie Guo, Kui Yu, Shuai Yang, Xiaoli Tang, Han Yu, and Mingcai Chen†. SFFedMC: Spurious-Free Federated Multi-View Clustering via Privacy-Preserving Confounder Balancing. Proceedings of the 34th ACM International Conference on Multimedia (ACM MM’26). [Acceptance Rate: ~26.5%]

Mingcai Chen, Baoming Zhang*, Zongbo Han, Wenyu Jiang, Yanmeng Wang, Shuai Feng, Yuntao Du, and Bingkun Bao. Test-Time Selective Adaptation for Uni-Modal Distribution Shift in Multi-Modal Data. Proceedings of the 42nd International Conference on Machine Learning (ICML’25). [Acceptance Rate: ~27%]

Mingcai Chen, Yuntao Du, Wenyu Jiang, Baoming Zhang, Shuai Feng, Yi Xin, and Chongjun Wang. Robust Logit Adjustment for Learning with Long-Tailed Noisy Data. Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI’25). [Acceptance Rate: ~23%]

Mingcai Chen, Yu Zhao*, Bing He, Zongbo Han, Junzhou Huang, Bingzhe Wu, and Jianhua Yao. Learning with Noisy Labels over Imbalanced Subpopulations. IEEE Transactions on Neural Networks and Learning Systems (TNNLS).

Mingcai Chen, Yu Zhao*, Bing He, Zhonghuang Wang, and Jianhua Yao. A Noisy-Label-Learning Formulation for Immune Repertoire Classification and Disease-Associated Immune Receptor Sequence Identification. Proceedings of the 32nd International Joint Conference on Artificial Intelligence (IJCAI’23). [Acceptance Rate: ~15%]

Mingcai Chen, Hao Cheng, Yuntao Du, Ming Xu, Wenyu Jiang, and Chongjun Wang. Two Wrongs Don’t Make a Right: Combating Confirmation Bias in Learning with Label Noise. Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI’23). [Acceptance Rate: ~20%]

Mingcai Chen, Yuntao Du, Yi Zhang, Shuwei Qian, and Chongjun Wang. Semi-Supervised Learning with Multi-Head Co-Training. Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI’22). [Acceptance Rate: ~15%]

Mingcai Chen, Yang Li, Yi-Heng Zhu, Fang Ge, and Dong-Jun Yu. SSCpred: Single-Sequence-Based Protein Contact Prediction Using Deep Fully Convolutional Network. Journal of Chemical Information and Modeling (JCIM).

Wenyu Jiang, Hao Cheng, Mingcai Chen, Chongjun Wang, and Hongxin Wei. DOS: Diverse Outlier Sampling for Out-of-Distribution Detection. Proceedings of the 12th International Conference on Learning Representations (ICLR’24).

Wenyu Jiang, Yuxin Ge, Hao Cheng, Mingcai Chen, Shuai Feng, and Chongjun Wang. READ: Aggregating Reconstruction Error into Out-of-distribution Detection. Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI’23).

Baoming Zhang, Ming Xu, Mingcai Chen, Mingyuan Chen, and Chongjun Wang. CopGAT: Co-propagation Self-supervised Graph Attention Network. Proceedings of the International Symposium on Parallel and Distributed Processing with Applications (ISPA’22).

Shuai Feng, Wenyu Jiang, Mingcai Chen, Yuntao Du, Hao Cheng, and Chongjun Wang. CESED: Exploiting Hyperspherical Predefined Evenly-Distributed Class Centroids for OOD Detection. Proceedings of the SIAM International Conference on Data Mining (SDM’23).

Yuntao Du, Juan Jiang, Hongtao Luo, Haiyang Yang, Mingcai Chen, and Chongjun Wang. Bidirectional View based Consistency Regularization for Semi-Supervised Domain Adaptation. Transactions on Machine Learning Research (TMLR).

* Equal contribution; † Corresponding author.