Short Bio

• Dr. Jichang Li is currently a Tenure-Track Associate Professor at the School of Computer Science and Engineering (CSE), Sun Yat-sen University (SYSU), where he is affiliated with the SYSU-HCP Lab. Prior to joining SYSU, he worked as an Assistant Researcher at the Research Institute of Multiple Agents and Embodied Intelligence, Pengcheng Laboratory, under the leadership of Prof. Liang Lin (IEEE Fellow). Previously, he earned his PhD in Computer Science at The University of Hong Kong (HKU), supervised by Prof. Yizhou Yu (ACM/IEEE Fellow) and co-supervised by Prof. Guanbin Li. Earlier, he received his M.Eng. degree in Computer Technology from South China University of Technology, advised by Prof. Si Wu and Prof. Zhiwen Yu.

🔬 We focus on cutting-edge research in Computer Vision and Machine Learning, with particular interests in:

• Spatial / Physical / Agentic / Embodied AI
• Foundation Models
• Visual Content Understanding
• Open-world Learning
• Weakly-supervised Learning

📢 We are looking for self-motivated PhD/Master students (for 2027 Fall intake) and Postdocs/RAs to join our group. If you are interested, please feel free to reach out via email.

Experiences

• Tenure-Track Associate Professor, Sun Yat-sen University, 2026-2026
• Assistant Researcher, Pengcheng Laboratory, 2024-2026
• Teaching Assistant, The University of Hong Kong, 2020-2024

Educations

• Doctorate of Philosophy (PhD) in Computer Science, The University of Hong Kong, 2020-2024
• Master of Engineering (M.Eng.) in Computer Technology, South China University of Technology, 2017-2020
• Bachelor of Engineering (B.Eng.) in Communication Engineering, South China Normal University, 2013-2017

📝 Publications

( # Equal contribution; * Corresponding author )

Conference

• Mobile-Agent-RAG: Driving Smart Multi-Agent Coordination with Contextual Knowledge Empowerment for Long-Horizon Mobile Automation
  Yuxiang Zhou#, Jichang Li#, Yanhao Zhang, Haonan Lu, and Guanbin Li
  The Fortieth AAAI Conference on Artificial Intelligence, 2026 (AAAI2026)
  [Project][Official][ArXiv][PDF][Video][Code][BibTex]

• DeepShield: Fortifying Deepfake Video Detection with Local and Global Forgery Analysis
  Yinqi Cai#, Jichang Li#, Zhaolun Li, Weikai Chen, Rushi Lan, Xi Xie, Xiaonan Luo, and Guanbin Li
  International Conference on Computer Vision, 2025 (ICCV2025)
  [Official][ArXiv][PDF][Supp][Code]

• FakeRadar: Probing Forgery Outliers to Detect Unknown Deepfake Videos
  Zhaolun Li, Jichang Li*, Yinqi Cai, Junye Chen, Xiaonan Luo, Guanbin Li, and Rushi Lan*
  International Conference on Computer Vision, 2025 (ICCV2025)
  [Official][ArXiv][PDF][Supp]

• Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection
  Jiaming Li, Jiacheng Zhang, Jichang Li, Ge Li, Si Liu, Liang Lin, and Guanbin Li
  The IEEE Conference on Computer Vision and Pattern Recognition, 2024 (CVPR2024)
  [PDF][ArXiv][Supp][BibTex]

• AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning
  Duojun Huang, Xinyu Xiong, Jie Ma, Jichang Li, Zequn Jie, Lin Ma, and Guanbin Li
  The IEEE Conference on Computer Vision and Pattern Recognition, 2024 (CVPR2024)
  [PDF][ArXiv][Supp][BibTex]

• FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels
  Jichang Li, Guanbin Li, Hui Cheng, Zicheng Liao, and Yizhou Yu
  The Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024 (AAAI2024)
  [Official][ArXiv][PDF][Full][Supp][BibTex]

• Divide and Adapt: Active Domain Adaptation via Customized Learning
  Duojun Huang, Jichang Li, Weikai Chen, Junshi Huang, Zhenhua Chai, and Guanbin Li
  The IEEE Conference on Computer Vision and Pattern Recognition, 2023 (CVPR2023 Highlight)
  [PDF][ArXiv][Supp][Code][BibTex]

• Neighborhood Collective Estimation for Noisy Label Identification and Correction
  Jichang Li, Guanbin Li, Feng Li, and Yizhou Yu
  European Conference on Computer Vision, 2022 (ECCV2022)
  [Official][PDF][ArXiv][Supp][Code][BibTex]

• Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation
  Jichang Li, Guanbin Li, Yemin Shi, and Yizhou Yu
  The IEEE Conference on Computer Vision and Pattern Recognition, 2021 (CVPR2021)
  [PDF][ArXiv][Supp][Code][BibTex]

• Mutual Learning of Complementary Networks via Residual Correction for Improving Semi-Supervised Classification
  Si Wu (Master Advisor), Jichang Li, Cheng Liu, Zhiwen Yu, and Hau-San Wong
  The IEEE Conference on Computer Vision and Pattern Recognition, 2019 (CVPR2019 Oral)
  [PDF][BibTex]

• Enhancing TripleGAN for Semi-Supervised Conditional Instance Synthesis and Classification
  Si Wu, Guangchang Deng, Jichang Li, Rui Li, Zhiwen Yu, and Hau-San Wong
  The IEEE Conference on Computer Vision and Pattern Recognition, 2019 (CVPR2019)
  [PDF][BibTex]

Journal

• Benefiting from OOD Samples in Open-Set Semi-Supervised Object Detection
  Yiqi Zou, Kuo Wang, Jichang Li*, Chuan Wang, Shuangyin Liu*, Liang Lin, and Guanbin Li*
  IEEE Transactions on Neural Networks and Learning Systems, 2026 (IEEE TNNLS2026)
  [Official][PDF]

• Decouple and Couple: Exploiting Prior Knowledge for Visible Video Watermark Removal
  Junye Chen, Chaowei Fang, Jichang Li, Yicheng Leng, and Guanbin Li
  IEEE Transactions on Image Processing, 2025 (IEEE TIP2025)
  [Official][PDF]

• Inter-Domain Mixup for Semi-Supervised Domain Adaptation
  Jichang Li, Guanbin Li, and Yizhou Yu
  Elsevier Pattern Recognition, 2023 (Elsevier PR2023)
  [PDF][ArXiv][ResearchGate][BibTex]

• Adaptive Betweenness Clustering for Semi-Supervised Domain Adaptation
  Jichang Li, Guanbin Li, and Yizhou Yu
  IEEE Transactions on Image Processing, 2023 (IEEE TIP2023)
  [Official][PDF][ArXiv][ResearchGate][BibTex]

• Semi-Supervised Deep Coupled Ensemble Learning with Classification Landmark Exploration
  Jichang Li, Si Wu, Cheng Liu, Zhiwen Yu, and Hau-San Wong
  IEEE Transactions on Image Processing, 2019 (IEEE TIP2019)
  [PDF][BibTex]

• Relation Classification via Keyword-Attentive Sentence Mechanism and Synthetic Stimulation Loss
  Luoqin Li, Jiabing Wang, Jichang Li, Qianli Ma, and Jia Wei
  IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2019 (IEEE/ACM TASLP2019)
  [PDF][BibTex]

Preprint

• Style-Preserving Lip Sync via Audio-Aware Style Reference
  Weizhi Zhong, Jichang Li, Yinqi Cai, Ming Li, Feng Gao, Liang Lin, Guanbin Li
  [ArXiv]

PhD Thesis

• Robust Visual Learning under Imperfection: Navigating Limited Supervision and Label Uncertainty
  Jichang Li
  [Official]

Professional Services

• Journal reviewers
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023-2026
  IEEE Transactions on Image Processing (TIP), 2023-2026
  IEEE Transactions on Multimedia (TMM), 2024
  IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025-2026
  IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2026
  IEEE Transactions on Artificial Intelligence (TAI), 2025-2026
  IEEE Transactions on Knowledge and Data Engineering (TKDE), 2026
  IEEE Transactions on Big Data (TBD), 2025
  IEEE Transactions on Mobile Computing (TMC), 2025
  IEEE Transactions on Communications (TCOM), 2026
  IEEE/ASME Transactions on Mechatronics, 2024
  Pattern Recognition, 2026
  Information Sciences, 2023-2024
  The Visual Computer, 2021

• Conference reviewers/program committee members
  IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2023-2026
  IEEE/CVF International Conference on Computer Vision (ICCV), 2023/2025
  European Conference on Computer Vision (ECCV), 2024/2026
  Annual Conference on Neural Information Processing Systems (NeurIPS), 2026
  AAAI Conference on Artificial Intelligence (AAAI), 2025-2026
  British Machine Vision Conference (BMVC), 2022/2026
  The IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2027
  Asian Conference on Computer Vision (ACCV), 2024/2026
  

Selected Honors and Awards

• Outstanding Reviewer, ICCV 2025
• HKU Postgraduate Scholarship, 2020-2024
• National Scholarship for Postgraduates (Top 1), 2020
• SCNU First-Prize Scholarship, 2016