刘文瑜，博士，副教授。2024年毕业于浙江大学获计算机技术专业博士学位。主要从事计算机视觉、人工智能安全和多模态大模型等方向的研究工作，近年来在国际权威期刊和会议上发表论文二十余篇，包括AAAI、ECCV、NeurIPS、IEEE TCSVT和IEEE TPAMI等， Google Scholar引用1500余次。同时担任AAAI、CVPR、ICCV、ECCV、ACM MM以及IEEE TIP、IEEE TCSVT、IEEE TITS、IEEE TMM等国际期刊和会议的审稿人。主持国家自然科学基金青年项目（C类）、福建省自然科学基金创青项目，福建省中青年教师教育科研重点项目。欢迎自驱力强、有较好的自学能力、编程能力以及英语水平的本科同学加入课题组，同时欢迎报考本人的研究生，招生专业：计算机科学与技术、人工智能。

1. 2012.9-2016.6, 哈尔滨工程大学，通信工程，本科

2. 2016.9-2019.6, 北京大学，电子与通信工程，硕士

3. 2019.7-2020.8, 小米人工智能实验室，视觉组，算法工程师

4. 2020.9-2024.6，浙江大学，计算机技术，博士

5. 2020.11-2023.11，阿里巴巴，通义实验室，算法工程师（兼职）

6. 2024.8-至今，福建师范大学，副教授

1.Wenyu Liu, Gaofeng Ren, Runsheng Yu, Shi Guo, Jianke Zhu, and Lei Zhang, “Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions”, AAAI2022. CCF A类会议

2.Wenyu Liu, Wentong Li, Jianke Zhu, and Lei Zhang, “Improving Nighttime Driving-Scene Segmentation via Dual Image-adaptive Learnable Filters.” IEEE TCSVT 2023. 一区TOP期刊

3.Wenyu Liu, Song Wang, Jianke Zhu, and Lei Zhang, “Domain Adaptation Transformer for Unsupervised Driving-Scene Segmentation in Adverse Conditions .” IEEE TITS 2024 一区TOP期刊

4.Wenyu Liu, Tianqiang Huang, Pengfei Zhang, Zong Ke, Minghui Min, and Puning Zhao, High Dimensional Distributed Gradient Descent with Arbitrary Number of Byzantine Attackers, AAAI2026. CCF A类会议

5.Changyi Ma, Zihan Fang, Lihua Zhou, Tao Li, Wenyu Liu†(Corresponding Author), Runsheng Yu†, and Xuan Song, Deep Noisy-Label Learning via Effective Rank Reduction, ECCV2026. CCF B类会议

6.Runsheng Yu*, Wenyu Liu*(Equal Contribution), Yasen Zhang, Deli Zhao, and Bo Zhang, Deepexposure: Learning to expose photos with asynchronously reinforced adversarial learning, NeurIPS2018. CCF A类会议 

7.Haifeng Luo, Shaocong Lin, Tianqiang Huang, Hanxian He, Runsheng Yu, and Wenyu Liu†(Corresponding Author), Imperceptible Adversarial Attacks for 3D Point Clouds Using Dimension Features and Gaussian Kernel Perturbations. Expert Systems with Applications, 2026. 一区TOP期刊

8.Xueying Chen, Tianqiang Huang†, Wenyu Liu†(Corresponding Author), Zhenghong Wang, Wentong Li, Wei Huang, Riqing Chen, and Haifeng Luo, Deepfakeclip: Semantic-opposite prompt learning for generalizable deepfake detection. Knowledge-Based Systems, 2025. 一区TOP期刊

9.Wentong Li, Wenyu Liu, Jianke Zhu, and Lei Zhang,Box2mask: Box-supervised instance segmentation via level set evolution IEEE TPAMI 2024. 一区TOP期刊

10.Song Wang, Wentong Li, Wenyu Liu, and Jianke Zhu, “LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation”, CVPR2023. CCF A类会议