陈明猜

发布时间：2025-04-17浏览次数：1330文章来源：计算机学院

职称：讲师（校聘副教授）

部门：计算机科学与技术系

研究方向：开放环境及低质量数据场景下的机器学习、深度学习方法，以及大模型的适配与应用。

个人简介

2024年6月博士毕业于南京大学计算机科学与技术系。2024年8月加入南京邮电大学计算机学院、软件学院、网络空间安全学院。研究主要致力于在开放环境下构建可靠、稳健的AI模型，包括噪声标签学习、分布外样本检测、分布偏移等。

近5年发表学术论文十余篇，以第一作者在ICML、AAAI、IJCAI、TNNLS等CCF-A类会议、顶级国际期刊上发表论文7篇。主持国家自然科学基金青年科学基金项目、江苏省自然科学基金青年项目、江苏省高等学校基础科学（自然科学）研究面上项目等。

欢迎相关专业同学与我联系，一起学习:)，邮箱：chenmc@njupt.edu.cn。

1. Mingcai Chen, Baoming Zhang*, Zongbo Han, Yuntao Du, Wenyu Jiang, Yanmeng Wang, Shuai Feng, Bingkun Bao.

Test-Time Selective Adaptation for Uni-Modal Distribution Shift in Multi-Modal Data.

Proceedings of the Forty-second International Conference on Machine Learning (ICML'25)

[Acceptance Rate: ~27%]

2. Mingcai Chen, Yuntao Du, Wenyu Jiang, Baoming Zhang, Shuai Feng, Yi Xin, Chongjun Wang.

Robust Logit Adjustment for Learning with Long-Tailed Noisy Data.

Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence (AAAI'25)

[Acceptance Rate: ~23%]

3. Mingcai Chen, Yu Zhao*, Bing He, Zongbo Han, Junzhou Huang, Jianhua Yao.

Learning with Noisy Labels over Imbalanced Subpopulations.

IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

4. Mingcai Chen, Yu Zhao*, Bing He, Zhonghuang Wang, 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%]

5. Mingcai Chen, Hao Cheng, Yuntao Du, Ming Xu, Wenyu Jiang, 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%]

6. 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%]