About Me
Hello, I’m Jinpeng Chen (陈锦芃), a Research Engineer at Huawei Hong Kong Research Center (HKRC). I received my Ph.D. in Computer Science from City University of Hong Kong, advised by Prof. Horace Ho Shing Ip and Prof. Sam Kwong (IEEE Fellow), and collaborated closely with Prof. Runmin Cong. My research focuses on continual learning, multimodal large language models (MLLMs), and image segmentation.
Experience
Huawei Hong Kong Research Center (Jun 2025 - Now)
Position: Research Engineer
Responsibilities: Explored multimodal understanding and AI Agent development.
Huawei Hong Kong Research Center (May 2024 - Apr 2025)
Position: Research Intern
Responsibilities: Investigated AI Agents and continual learning strategies for multimodal large language models (MLLMs).
Tsinghua University (Aug 2019 - Jun 2021)
Position: Research Intern
Responsibilities: Conducted research on AI-driven analysis and applications of human physiological signals.
Education
City University of Hong Kong (Sep 2021 - Jun 2025)
Degree: Ph.D.
Major: Computer Science
Supervisor: Prof. Horace Ip and Prof. Sam Kwong (IEEE Fellow)
Research Focus: Continual Learning, MLLMs, Image Segmentation
GPA: 3.90/4.3
Beijing University of Posts and Telecommunications (Sep 2017 - Jun 2021)
Degree: B.Eng.
Major: Electronic Information Science and Technology
GPA: 3.63/4.0
Publications
Jinpeng Chen†, Runmin Cong†, Yuzhi Zhao, Hongzheng Yang, Guangneng Hu, Horace Ho Shing Ip, and Sam Kwong, “SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning,” ICML, 2025. [Paper] [Code] [Dataset]
Jinpeng Chen, Runmin Cong, Yuxuan Luo, Horace Ho Shing Ip, and Sam Kwong, “Replay without saving: Prototype derivation and distribution rebalance for class-incremental semantic segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025. [Paper] [Code]
Jinpeng Chen, Runmin Cong, Yuxuan Luo, Horace Ho Shing Ip, and Sam Kwong, “Strike a balance in continual panoptic segmentation,” ECCV, 2024. [Paper] [Code]
Jinpeng Chen, Runmin Cong, Horace Ho Shing Ip, and Sam Kwong, “KepSalinst: Using peripheral points to delineate salient instances,” IEEE Transactions on Cybernetics, 2024. [Paper] [Code]
Jinpeng Chen, Runmin Cong, Yuxuan Luo, Horace Ho Shing Ip, and Sam Kwong, “Saving 100x storage: Prototype replay for reconstructing training sample distribution in class-incremental semantic segmentation,” NeurIPS, 2023. [Paper] [Code]
Yuxuan Luo†, Jinpeng Chen†, Runmin Cong, Horace Ho Shing Ip, and Sam Kwong, “Trace back and go ahead: Completing partial annotation for continual semantic segmentation,” Pattern Recognition, 2025. [Paper]
Runmin Cong, Hang Xiong, Jinpeng Chen‡, Wei Zhang, Qingming Huang, and Yao Zhao, “Query-guided prototype evolution network for few-shot segmentation,” IEEE Transactions on Multimedia, 2024. [Paper] [Code]
Runmin Cong, Yuchen Guan, Jinpeng Chen‡, Wei Zhang, Yao Zhao, and Sam Kwong, “SDDNet: Style-guided dual-layer disentanglement network for shadow detection,” ACM MM, 2023. [Paper] [Code]
Yuxuan Luo, Jinpeng Chen, Runmin Cong, Horace Ho Shing Ip, and Sam Kwong, “Query-guided prototype evolution network for few-shot segmentation,” IEEE Transactions on Circuits and Systems for Video Technology, 2025. [Paper]
Hang Xiong, Runmin Cong, Jinpeng Chen, Chen Zhang, Feng Li, Huihui Bai, and Sam Kwong, “MM-Prompt: Multi-modality and Multi-granularity Prompts for Few-Shot Segmentation,” ACM MM, 2025.
(†Co-first Author; ‡Corresponding Author)