韩忠义（1994），博士，山东大学软件学院教授，博士生导师，齐鲁青年学者。研究兴趣主要包含机器学习、基础模型、Agentic AI、AI for Science、医学图像处理等，聚焦于开放环境下鲁棒机器学习理论与方法的基础研究，围绕数据分布变化、数据类别变化与数据标记受限等核心挑战，系统性地解决了鲁棒域自适应、分布外检测与弱监督学习等关键科学问题。迄今已在TPAMI、IJCV、TIP、TKDE、MLJ、TMI、MedIA、NeurIPS、CVPR、AAAI、IJCAI、IPMI等顶级期刊和会议发表论文40余篇，授权发明专利6件，2篇入选ESI高被引论文，谷歌学术总引用超过2500次。长期担任TPAMI、IJCV、TIP、TNNLS等国际顶级期刊，以及ICML、NeurIPS、ICLR、CVPR、ICCV、ECCV等人工智能领域顶级会议的审稿人或高级程序委员会委员。获得2023年青岛市科技进步二等奖、2025年CCF人工智能与模式识别专委会博士学位论文激励计划，2024年山东省优秀博士学位论文奖、ACM（济南）2023年优博奖，山东省人工智能学会优博与优秀硕士学位论文，并被评为NeurIPS 2024与IEEE TMI 2022杰出审稿人，研究成果入选2023年度山东省人工智能优秀论文。参与国家自然科学基金（重点、面上）、国家重点研发计划、山东省重大基础研究等项目近10项。

Google Scholar: https://scholar.google.com/citations?user=0J-PErUAAAAJ&hl=en

学术交流：

2016.12 - 2018.02: 加拿大西安大略大学联培，医学图像处理；

2018.02 - 2018.12: 百度视觉技术部实习，医学图像处理；

2019.03 - 2020.01: 南京大学LAMDA实验室联培，机器学习。

所在团队：

山东大学人工智能研究中心

山东大学机器学习与数据挖掘实验室

招生信息：

1） 招收2026年研究生

2）招收若干本科实习生

招收若干本科生实习生，有意向在本科就读阶段接触研究生科研工作、发表高水平学术论文或竞赛指导可咨询联系（建议位于一年级下学期、二年级、三年级上学期的学生主动联系）。持续接受学术培养的本科实习生，目前保研率、海外研究生申请成功率100%。

代表性论文：

*通讯作者；#共同一作

贡献 1：开放环境下鲁棒域自适应理论和方法

[1] Zhongyi Han, Xian-Jin Gui, Haoliang Sun, Yilong Yin*, Shuo Li. Towards Accurate and Robust Domain Adaptation Under Multiple Noisy Environments. IEEE Transactions on Pattern Analysis and Machine Intelligence (IF: 24.3, CCF-A). 2022. DOI: 10.1109/TPAMI.2022.3215150.

[2] Zhongyi Han, Haoliang Sun, Yilong Yin*. Learning Transferable Parameters for Unsupervised Domain Adaptation. IEEE Transactions on Image Processing (IF: 10.8, CCF-A). 2022. DOI: 10.1109/TIP.2022.3184848.

[3] Zhongyi Han, Gongxu Luo, Yaqian Li, Bo Han, Mingming Gong, Kun Zhang, Tongliang Liu*. AlignCLIP: Navigating the Misalignments for Robust Vision-Language Generalization. Machine Learning. 2025. DOI: 10.1007/s10994-025-06742-z.

[4] Zhongyi Han, Zhiyan Zhang, Fan Wang, Rundong He, Wan Su, Xiaoming Xi, Yilong Yin*. Discriminability and Transferability Estimation: A Bayesian Source Importance Estimation Approach for Multi-Source-Free Domain Adaptation. AAAI Conference on Artificial Intelligence (AAAI, CCF-A). 2023. DOI: 10.1609/aaai.v37i6.25946.

[5] Zhongyi Han, Xian-Jin Gui, Chaoran Cui*, Yilong Yin*. Towards Accurate and Robust Domain Adaptation under Noisy Environments. International Joint Conference on Artificial Intelligence (IJCAI, CCF-A). 2020. DOI: 10.24963/ijcai.2020/314.

贡献 2：开放环境下鲁棒分布外检测理论和方法

[1] Rundong He, Zhongyi Han*, Xiushan Nie, Yilong Yin, Xiaojun Chang. Visual Out-of-Distribution Detection in Open-Set Noisy Environments. International Journal of Computer Vision (IF: 11.6, CCF-A). 2024. DOI: 10.1007/s11263-024-02139-y.

[2] Rundong He, Zhongyi Han*, Xiankai Lu, Yilong Yin*. SAFER-STUDENT for Safe Deep Semi-Supervised Learning with Unseen-Class Unlabeled Data. IEEE Transactions on Knowledge and Data Engineering (IF: 10.2, CCF-A). 2023. DOI: 10.1109/TKDE.2023.3279139.

[3] Wan Su, Zhongyi Han*, Rundong He, Benzheng Wei, Xueying He, Yilong Yin. Neighborhood-based Credibility Anchor Learning for Universal Domain Adaptation. Pattern Recognition (IF: 8.3, CCF-B). 2023. DOI: 10.1016/j.patcog.2023.109686.

[4] Rundong He#, Yue Yuan#, Zhongyi Han*, Fan Wang, Wan Su, Yilong Yin*, Tongliang Liu, Yongshun Gong. Exploring Channel-Aware Typical Features for Out-of-Distribution Detection. AAAI Conference on Artificial Intelligence (AAAI, CCF-A). 2024. DOI: 10.1609/aaai.v38i11.29132.

[5] Yue Yuan#, Rundong He#, Zhongyi Han*, Yilong Yin*. LHAct: Rectifying Extremely Low and High Activations for Out-of-Distribution Detection. ACM Multimedia (ACM MM, CCF-A). 2023. DOI: 10.1145/3581783.3611720.

贡献 3：开放环境下鲁棒弱监督医学影像分析

[1] Zhongyi Han, Benzheng Wei*, Yanfei Hong, Tianyang Li, Jinyu Cong, Xue Zhu, Haifeng Wei, Wei Zhang*. Accurate Screening of COVID-19 using Attention Based Deep 3D Multiple Instance Learning. IEEE Transactions on Medical Imaging (IF: 11.0, CCF-B). 2020. DOI: 10.1109/TMI.2020.2996256.

[2] Zhongyi Han, Benzheng Wei*, Xiaoming Xi, Bo Chen, Yilong Yin*, Shuo Li. Unifying Neural Learning and Symbolic Reasoning for Spinal Medical Report Generation. Medical Image Analysis (IF: 12.1, CCF-C). 2020. DOI: 10.1016/j.media.2020.101872.

[3] Zhongyi Han, Benzheng Wei*, Ashley Mercado, Stephanie Leung, Shuo Li*. Spine-GAN: Semantic Segmentation of Multiple Spinal Structures. Medical Image Analysis (IF: 12.1, CCF-C). 2018. DOI: 10.1016/j.media.2018.08.005.

[4] Zhongyi Han, Benzheng Wei*, Stephanie Leung, Jonathan Chung, Shuo Li*. Towards Automatic Report Generation in Spine Radiology Using Weakly Supervised Framework. Medical Image Computing and Computer-Assisted Intervention (MICCAI, CCF-B). 2018. DOI: 0.1007/978-3-030-00937-3_22.
[5] Zhongyi Han, Rundong He, Tianyang Li, Benzheng Wei*, Jian Wang, Yilong Yin*. Semi-Supervised Screening of COVID-19 from Positive and Unlabeled Data with Constraint Non-Negative Risk Estimator. International Conference on Information Processing in Medical Imaging (IPMI). 2021. DOI: 10.1007/978-3-030-78191-0_47.

2025.07 -- 至今

山东大学      软件学院      教授

2023.04 -- 2024.01

穆罕默德·本·扎耶德人工智能大学 (MBZUAI)      机器学习系      博士后研究员

2024.01 -- 2025.07

阿卜杜拉国王科技大学（KAUST）      生成式人工智能卓越研究中心      博士后研究员