个人简介

吴科君 (教师主页) ，博士，IEEE高级会员，研究生导师，现任华中科技大学电子信息与通信学院讲师/助理教授。在此之前，他于新加坡南洋理工大学电气电子工程学院从事博士后研究（与Yap Kim-Hui、周立培教授，IEEE Fellow）。他的研究兴趣主要包括多模态大模型、字节语言模型、生成模型等领域，近5年在IEEE T-MM、NeurIPS、ACM Multimedia等高水平期刊、会议发表论文50余篇。担任IEEE OJSP、ASOC、JRTIP、JVCI等权威期刊副编辑，并在国际会议AAAI 2026、PRCV 2026、AIGC 2025、IJCNN 2025、ICASSP2024、ISCAS2024及MMSP2023中担任PC Member/讲习班主席/领域主席/专题主席等。入选中国电子学会青年科技人才培育工程，主持及参与国家自然科学基金等项目多项。
🚀 招收兴趣从事以上研究领域的研究生、研究助理、实习生等 (长期有效)。

Biography

Dr. Kejun Wu (Faculty HomePage) is currently a Lecturer/Assistant Professor at School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China. Before that, he worked as a Research Fellow researcher at School of Electrical and Electronic Engineering, Nanyang Technological University (with Prof. Yap Kim-Hui and Chau Lap-Pui, IEEE Fellow). His research interest includes Multimodal Large Language Models, Byte Language Models, and Generative Models. He has over 50 publications in top-tier venues in the past 5 years. He serves as an Associate Editor / Editorial Board Member of IEEE OJSP, ASOC, JRTIP, and JVCI, etc., an Area /Tutorial /Session Chair / Program Committee in AAAI 2026, PRCV 2026, IJCNN 2026, AIGC 2025, IJCNN 2025, IEEE ICASSP 2024,ISCAS 2024, and MMSP2023. He is an IEEE Senior Member.
🚀 Recruiting intern/ visiting/ Master students. On-site, remote, or hybrid learning are welcome.

学术服务

编委, 国际期刊Applied Soft Computing
副编辑, 国际期刊IEEE Open Journal of Signal Processing
副编辑, 国际期刊Journal of Real-Time Image Processing
副编辑, 国际期刊Journal of Visual Communication and Image Representation
客座编辑,《电子与信息学报》中国科技期刊卓越行动计划中文领军期刊、CCF-T1类
讲习班主席, 领域主席, 国际会议PRCV 2026, 哈尔滨
Program Committee, 世界人工智能大会·学术 (WAICA 2026), 上海
Program Committee, AAAI 2027(加拿大), AAAI 2026(新加坡)
领域主席, 国际会议IJCNN 2026(荷兰), IJCNN 2025(意大利)
程序委员会, 国际会议AIGC 2026, AIGC 2025
专题主席, 国际会议ISCAS 2024, 新加坡
专题主席, 国际会议ICASSP 2024, 韩国
专题主席, 国际会议MMSP 2023, 法国
应急态势感知与应急通信技术决策咨询专家团队成员, 中国科协
UWA技术规划组专家, 世界超高清视频产业联盟UWA
Technical Committee Affiliate, Image, Video, and Multidimensional Signal Processing (IVMSP), IEEE 信号处理学会
Technical Committee Affiliate, Multimedia Signal Processing (MMSP), IEEE 信号处理学会
审稿人：IEEE TMM, IEEE TCSVT, IEEE TBc, Pattern Recognition, Information Fusion, NeurIPS, AAAI, ICASSP, etc.

Professional Activities

Editorial Board, Applied Soft Computing
Associate Editor, IEEE Open Journal of Signal Processing
Associate Editor, Journal of Real-Time Image Processing
Associate Editor, Journal of Visual Communication and Image Representation
Guest Editor, Journal of Electronics & Information Technology
Tutorial Chair, Area Chair, PRCV 2026, Harbin
Program Committee, WAIC Academic 2026 (WAICA2026), Shanghai, China
Program Committee, AAAI 2027(Canada), AAAI 2026(Singapore)
Area Chair, IJCNN 2026(Netherlands), IJCNN 2025(Italy)
Program Committee, Session Chair, AIGC 2025, Hangzhou, China
Session Chair, IEEE ISCAS 2024, Singapore
Session Chair, IEEE ICASSP 2024, Korea
Session Chair, IEEE MMSP 2023, France
Member, 应急态势感知与应急通信技术决策咨询专家团队, 中国科协
Experts, UWA Technical Planning Expert Group, UHD World Association (UWA, 世界超高清视频产业联盟)
Technical Committee Affiliate, Image, Video, and Multidimensional Signal Processing (IVMSP), IEEE Signal Processing Society (SPS)
Technical Committee Affiliate, Multimedia Signal Processing (MMSP), IEEE SPS
Reviewer of IEEE TMM, IEEE TCSVT, IEEE TBc, Pattern Recognition, Information Fusion, NeurIPS, AAAI, ICASSP, etc.

新闻动态

2026.09: 🏆2025级硕士研究生获2026年研究生国家奖学金，祝贺Fangcheng
2026.08: 受邀在第九届中国模式识别与计算机视觉大会(PRCV 2026，哈尔滨)作学术报告
2026.07: 1 篇论文被ACM Multimedia 2026录用（CCF-A），巴西
2026.05: 受邀在中国图像图形大会(CCIG 2026，广州)作学术报告
2026.03: 共同在《电子与信息学报》组织专题
2026.01: 共同在CVPR2026组织NTIRE Bitstream-corrupted Video Restoration挑战赛
2025.11: 获亚太人工智能教育优秀青年学者奖
2025.11: 获亚太人工智能教育优秀案例奖
2025.10: 获全国电子信息类专业高校教师智慧教学案例竞赛(浩埔杯)中南赛区二等奖
2025.07: 受邀在2025 Discover At HUST Metavers国际暑期学校英语授课
2025.07: 2 篇论文被ACM Multimedia 2025录用（CCF-A），爱尔兰
2025.06: 1 篇论文被 IEEE Transactions on Multimedia 录用
2024.11: 2 篇论文被 IEEE Transactions on Multimedia 录用
2024.05: 受邀担任 IEEE ISCAS 2024国际会议专题主席，新加坡
2024.04: 受邀担任 IEEE ICASSP 2024国际会议专题主席，韩国
2024.01: 2 篇论文被 Optics Express 和 Optics Letters 录用
2023.12: 获中国国际大学生创新大赛全国金奖
2023.11: 获中国博士后创新创业大赛海外赛全国铜奖
2023.10: 获春晖杯中国留学人员创新创业大赛优胜奖
2023.09: 受邀担任 IEEE MMSP 2023国际会议专题主席，法国
2023.09: 1 篇论文被 NeurIPS 2023录用（CCF-A），美国

News

2026.09: 🏆My student was awarded the 2026 National Scholarship for Graduate Students. Congratulations to Fangcheng
2026.08: Invited to give a Talk in The 9th Chinese Conference on Pattern Recognition and Computer Vision (PRCV2026, Harbin)
2026.07: 1 paper is accepted by ACM Multimedia 2026, Brazil
2026.05: Invited to give a Talk in Chinese Congress on Image and Graphics (CCIG 2026, Guangzhou)
2026.03: Serve as Guest Editor in Journal of Electronics & Information Technology
2026.01: Serve as Organizer in NTIRE Bitstream-corrupted Video Restoration Challenge @ CVPR 2026
2025.11: Awarded the Outstanding Young Scholar of Asia-Pacific Artificial Intelligence Education
2025.11: Awarded the Excellent Case Award of Asia-Pacific Artificial Intelligence Education
2025.07: Invited to lecture (in English) the 2025 Discover At HUST--"Metavers" International Summer School
2025.07: 2 papers are accepted by 33rd ACM International Conference on Multimedia (ACM Multimedia 2025), Dublin, Ireland
2025.06: 1 paper is accepted by IEEE Transactions on Multimedia (Corresponding Author)
2025.06: Serve as Program Committee for International Conference on AI-Generated Content (AIGC 2025), Hangzhou
2024.11: 2 papers are accepted by IEEE Transactions on Multimedia (中科院一区TOP，JCR Q1)
2024.05: I am appointed as Session Chair by IEEE ISCAS 2024, Singapore
2024.04: I am appointed as Session Chair by IEEE ICASSP 2024, Korea
2024.01: 2 papers are accepted by Optics Express and Optics Letters
2023.12: I am awarded the 全国金奖 in 中国国际大学生创新大赛
2023.11: I am awarded the 全国铜奖 in 中国博士后创新创业大赛
2023.10: I am awarded the 优胜奖 in 春晖杯中国留学人员创新创业大赛
2023.09: I am appointed as Session Chair by IEEE MMSP 2023, France
2023.09: 1 paper has been accepted by NeurIPS 2023, New Orleans, USA

论文发表

W. Liu, T. Liu, D. Zhang, K. Wu, A. Kong, “DriftAD: Visually-Guided Text Drift for Few-Shot Industrial Anomaly Detection,” in ACM MM 2026. (CCF-A)
T. Liu, K. Wu, C. Cai, Y. Wang, K. Yap, L. Chau, “Towards Blind Bitstream-corrupted Video Recovery: A Visual Foundation Model-driven Framework,” in ACM MM 2025. (CCF-A)
C. Cai, T. Liu, J. Gao, W. Liu, K. Wu*, R. Wang, Y. Wang, S. Liew, “From Semantics, Scene to Instance-awareness: Distilling Foundation Model for Open-vocabulary Grounded Situation Recognition,” in ACM MM 2025. (Corresponding Author, CCF-A)
T. Liu, K. Wu*, Y. Wang, W. Liu, K. Yap, and L. Chau, “Bitstream corrupted Video Recovery: A Novel Benchmark Dataset and Method,” NeurIPS 2023. (Equal Contribution, CCF-A)
W. Liu, C. Cai, J. Gao, K. Wu*, Y. Wang, K. Yap, and L. Chau, “PromptSR: Cascade Prompting for Lightweight Image Super-Resolution,” in IEEE Transactions on Multimedia, 2026. (Corresponding Author, 中科院1区TOP, CCF-A)
K. Wu, Z. Li, Y. Yang, Q. Liu, and X. Zhang, “End-to-end Deep Video Compression Based on Hierarchical Temporal Context Learning,” in IEEE Transactions on Multimedia, 27:4386-4399, 2025. (中科院1区TOP)
W. Liu, K. Wu*, T. Liu, Y. Wang, K. Yap, and L. Chau, “ByteNet: Rethinking Multimedia File Fragment Classification through Visual Perspectives,” in IEEE Transactions on Multimedia, 27:1305-1319, 2025. (Corresponding Author)
K. Wu, Y. Yang, Q. Liu, G. Jiang, and X. Zhang, “Hierarchical Independent Coding Scheme for Varifocal Multiview Images based on Angular-focal Joint Prediction,” IEEE Transactions on Multimedia, 26:2993-3006, 2024. (中科院1区TOP) $\color{Tomato} {ESI Highly Cited Papers}$
K. Wu, Y. Yang, Q. Liu, and X. Zhang, “Focal Stack Image Compression Based on Basis-Quadtree Representation,” in IEEE Transactions on Multimedia, 25:3975-3988, 2023. (中科院1区TOP)
K. Wu, Q. Liu, Y. Yang, and X. Zhang, “Gaussian-Wiener Representation and Hierarchical Coding Scheme for Focal Stack Images,” in IEEE Transactions on Circuits and Systems for Video Technology, 32(2):523-537, 2022. (中科院1区TOP)
K. Wu, S. Wang, J. Gao, W. Liu, Q. Liu, C. Cai, and Y. Yang, “LLMArk: Instance-aware Foundation Model for Flood Risk Assessment,” in Information Fusion, 2026. (中科院1区TOP, IF 17.4)
J. Liang, et al. “Cibic: Pixel-free Foundation Model for Robust Corrupted Image Bitstream Captioning,” Pattern Recognition, 2026 (中科院1区TOP).
K. Wu, et al. “Corrupted Bitstream Semantic Understanding by Adaptive-modal Large Manguage Models,” Pattern Recognition, 2026 (中科院1区TOP).
F. Li, et al. “Bitstream Action Recognition is Byte Modeling.” arXiv preprint arXiv:2608.15695 (2026).
X. Hu, et al. “AesCanvas: A Large-Scale Dataset and Benchmark for Aesthetic Critique and Contextual Suitability.” arXiv preprint arXiv:2608.26713v1 (2026).
C. Huang, et al. “Towards Bitstream-corrupted Harsh Visual Understanding: Through Bitstream Language Modeling as Robust Semantic Priors.” arXiv preprint arXiv:2608.21837 (2026).
J. Chen, et al. “FLM: Frequency-Aware Language Models for Generative Image Compression.” arXiv preprint arXiv:2608.28687 (2026).
J. Zhang, et al. “M3SunAgent: Monocular 3D Spatial Understanding Agent for Metric Depth Estimation and 3D Visual Grounding.” arXiv preprint arXiv:2610.07982 (2026).
Z. Yu, et al. “Image Bitstream Fine-grained Understanding for Privacy-Friendly AIoT.” arXiv preprint arXiv:2610.08414 (2026).

Selected Publications

W. Liu, T. Liu, D. Zhang, K. Wu, A. Kong, “DriftAD: Visually-Guided Text Drift for Few-Shot Industrial Anomaly Detection,” in ACM MM 2026.
T. Liu, K. Wu, C. Cai, Y. Wang, K. Yap, L. Chau, “Towards Blind Bitstream-corrupted Video Recovery: A Visual Foundation Model-driven Framework,” in ACM MM 2025.
C. Cai, T. Liu, J. Gao, W. Liu, K. Wu*, R. Wang, Y. Wang, S. Liew, “From Semantics, Scene to Instance-awareness: Distilling Foundation Model for Open-vocabulary Grounded Situation Recognition,” in ACM MM 2025. (Corresponding Author)
T. Liu, K. Wu*, Y. Wang, W. Liu, K. Yap, and L. Chau, “Bitstream corrupted Video Recovery: A Novel Benchmark Dataset and Method,” NeurIPS 2023. (Equal Contribution)
W. Liu, C. Cai, J. Gao, K. Wu*, Y. Wang, K. Yap, and L. Chau, “PromptSR: Cascade Prompting for Lightweight Image Super-Resolution,” in IEEE Transactions on Multimedia, 2026. (Corresponding Author)
K. Wu, Z. Li, Y. Yang, Q. Liu, and X. Zhang, “End-to-end Deep Video Compression Based on Hierarchical Temporal Context Learning,” in IEEE Transactions on Multimedia, 27:4386-4399, 2025
W. Liu, K. Wu*, T. Liu, Y. Wang, K. Yap, and L. Chau, “ByteNet: Rethinking Multimedia File Fragment Classification through Visual Perspectives,” in IEEE Transactions on Multimedia, 27:1305-1319, 2025. (Corresponding Author)
K. Wu, Y. Yang, Q. Liu, G. Jiang, and X. Zhang, “Hierarchical Independent Coding Scheme for Varifocal Multiview Images based on Angular-focal Joint Prediction,” IEEE Transactions on Multimedia, 26:2993-3006, 2024. $\color{Tomato} {ESI Highly Cited Papers}$
K. Wu, Y. Yang, Q. Liu, and X. Zhang, “Focal Stack Image Compression Based on Basis-Quadtree Representation,” in IEEE Transactions on Multimedia, 25:3975-3988, 2023.
K. Wu, Q. Liu, Y. Yang, and X. Zhang, “Gaussian-Wiener Representation and Hierarchical Coding Scheme for Focal Stack Images,” in IEEE Transactions on Circuits and Systems for Video Technology, 32(2):523-537, 2022.
K. Wu, S. Wang, J. Gao, W. Liu, Q. Liu, C. Cai, and Y. Yang, “LLMArk: Instance-aware Foundation Model for Flood Risk Assessment,” in Information Fusion, 2026. (IF 17.4)
J. Liang, et al. “Cibic: Pixel-free Foundation Model for Robust Corrupted Image Bitstream Captioning,” Pattern Recognition, (2026).
K. Wu, et al. “Corrupted Bitstream Semantic Understanding by Adaptive-modal Large Manguage Models“,” Pattern Recognition, (2026).
F. Li, et al. “Bitstream Action Recognition is Byte Modeling.” arXiv preprint arXiv:2608.15695 (2026).
X. Hu, et al. “AesCanvas: A Large-Scale Dataset and Benchmark for Aesthetic Critique and Contextual Suitability.” arXiv preprint arXiv:2608.26713v1 (2026).
C. Huang, et al. “Towards Bitstream-corrupted Harsh Visual Understanding: Through Bitstream Language Modeling as Robust Semantic Priors.” arXiv preprint arXiv:2608.21837 (2026).
J. Chen, et al. “FLM: Frequency-Aware Language Models for Generative Image Compression.” arXiv preprint arXiv:2608.28687 (2026).
J. Zhang, et al. “M3SunAgent: Monocular 3D Spatial Understanding Agent for Metric Depth Estimation and 3D Visual Grounding.” arXiv preprint arXiv:2610.07982 (2026).
Z. Yu, et al. “Image Bitstream Fine-grained Understanding for Privacy-Friendly AIoT.” arXiv preprint arXiv:2610.08414 (2026).

荣誉奖项

施普林格·自然杰出编辑奖(编辑贡献奖 & 作者服务奖)
亚太人工智能教育优秀青年学者
亚太人工智能教育优秀案例奖
春晖杯中国留学人员创新创业大赛优胜奖（排一，教育部）
全国博士后创新创业大赛铜奖（排一，人力资源和社会保障部）
中国国际大学生创新创业大赛湖北省金奖（排二，湖北省教育厅）
中国国际大学生创新创业大赛全国金奖（原互联网+，教育部）
全国高校电子信息实践教育大会教学案例二等奖
全国电子信息类专业高校教师智慧教学案例竞赛(浩埔杯)中南赛区二等奖

Honors & Awards

Springer Nature Editor of Distinction Awards (Editorial Contribution Award, Author Service Award)
Outstanding Young Scholar in Asia-Pacific Artificial Intelligence Education
Excellent Case Award in Asia-Pacific Artificial Intelligence Education
China International College Students' Innovation Competition (formerly Internet +, Gold Award)
National Postdoctoral Innovation and Entrepreneurship Competition (Bronze Award, ranked first)
Chunhui Cup Innovation and Entrepreneurship Competition for Chinese Overseas Students (ranked first)

受邀报告

第九届中国模式识别与计算机视觉大会(PRCV 2026, 哈尔滨), 面向多模态理解的图像-码流基础模型
中国图像图形大会(CCIG 2026, 广州), 真实世界图像码流损坏下语义内容理解
第三届人工智能生成内容国际会议暨大模型应用创新大会(AIGC 2025, 杭州), 重新思考大模型对数据损坏的脆弱性——一个字节域视角的尝试

Talks

The 9th Chinese Conference on Pattern Recognition and Computer Vision (PRCV2026, Harbin)
China Society of Image and Graphics (CSIG 2026, Guangzhou)
The 3rd International Conference on AI-Generated Content (AIGC 2025, Hangzhou)

教育经历

联合培养博士研究生，新加坡南洋理工大学电气与电子工程学院
博士学位，华中科技大学电子信息与通信学院
硕士学位，哈尔滨工程大学智能科学与工程学院
学士学位，上海大学机电工程与自动化学院

Educations

Exchange Ph.D Student, School of Electrical and Electronic Engineering, Nanyang Technological University
Ph.D Student, School of Electronic Information and Communications, Huazhong University of Science and Technology
Master Student, College of Intelligent Science and Engineering, Harbin Engineering University
Undergraduate Student, School of Mechatronic Engineering and Automation, Shanghai University

学生培养

我很荣幸能参与到这些优秀学生的培养过程:

J. Gao, W. Liu, T. Liu, Ph.D Student, NTU, Singapore (LLMs, restoration)
H. Dong, Intern Student, Columbia University, New York, USA (Trustworthy MLLM)
Q. Zhang, J. Liang, Intern Student, KTH Royal Institute of Technology, Sweden (Genomic language models, gLM)
F. Li, J. Chen, J. Zhang, Z. Yu, C. Huang, Master Student, HUST (Byte Language Models, Generative Compression, Spatial Agent)
Q. An, Q. Zeng, Z. Liu, X. Hu, Z. Liao, H. Shi, H. Xie, J. Wan, S. Li, J. Jiang, P. Lv, S. Mai, C. Sun, et.al. Intern Student, HUST (MLLMs, Agent)

Students

I'm honored to have participated in the supervision of these excellent students:

J. Gao, W. Liu, T. Liu, Ph.D Student, NTU, Singapore (LLMs, restoration)
H. Dong, Intern Student, Columbia University, New York, USA (Trustworthy MLLM)
Q. Zhang, J. Liang, Intern Student, KTH Royal Institute of Technology, Sweden (Genomic language models, gLM)
F. Li, J. Chen, J. Zhang, Z. Yu, C. Huang, Master Student, HUST (Byte Language Models, Generative Compression, Spatial Agent)
Q. An, Q. Zeng, Z. Liu, X. Hu, Z. Liao, H. Shi, H. Xie, J. Wan, S. Li, J. Jiang, P. Lv, S. Mai, C. Sun, et.al. Intern Student, HUST (MLLMs, Agent)

教学信息

2026秋, 机器智能课程设计
2026春, 深度学习
2026春, 数据挖掘
2026春, 数字语音处理

Teaching

2026 Spring, Machine Intelligence Course Design
2026 Spring, Deep Learning
2026 Spring, Data Mining
2026 Spring, Digital Speech Processing

Kejun Wu(吴科君)