Xinpeng Ding
About Me
Xinpeng Ding
Xinpeng Ding is a Professor at the Hangzhou Institute of Technology, Xidian University, and a member of the National Key Laboratory of Space-Ground Integrated Information Technology. He is a national-level young talent. He received his B.S. degree (2018) and M.S. degree (2021) from Xidian University under the supervision of Prof. Xinbo Gao and Prof. Nannan Wang, and his Ph.D. degree (2025) from the Hong Kong University of Science and Technology (HKUST) under the supervision of Prof. Xiaomeng Li.
His research interests include Embodied AI, Video Understanding, Multimodal Large Language Models, Computer Vision, and Medical Image Processing. He has published more than 30 papers on top-tier journals and conferences, including IJCV, CVPR, ICCV, ECCV, ICLR, ICML, TIP, TMI, MICCAI, and IJCAI. He previously worked as a Research Intern at Huawei Noah's Ark Lab and Alibaba DAMO Academy.
10
Journal/Conference
Publications
Education
Education & Experience
- 2026.02 - Present: Professor, Hangzhou Institute of Technology, Xidian University
- 2025.08 - 2026.01: Postdoctoral Researcher, HKUST
- 2024.05 - 2025.05: Research Intern, Huawei Noah's Ark Lab, Hong Kong
- 2021.09 - 2025.07: Ph.D. in Electronic and Computer Engineering, HKUST (Advisor: Prof. Xiaomeng Li)
- 2020.07 - 2021.07: Research Intern, Alibaba DAMO Academy, Hangzhou
- 2018.09 - 2021.07: M.S. in Information and Communication Engineering, Xidian University (Advisors: Prof. Xinbo Gao, Prof. Nannan Wang)
- 2014.08 - 2018.07: B.S. in Software Engineering, Xidian University
Selected Publications
2026
- Bin Pu, Siyu Wang, Rongbin Li, Xinpeng Ding, Lei Zhao, Chaoqi Chen, Shengli Li, Kenli Li: Organ-Aware Routing Mixture-of-Retrieval Augmented Generation for Fetal Ultrasound Reporting. AAAI, 2026.
2025
- Xinpeng Ding, Jianhua Han, Hang Xu, Wei Zhang, Xiaomeng Li: HiLM-D: Enhancing MLLMs with Multi-scale High-Resolution Details for Autonomous Driving. IJCV, 2025.
- Guozhang Li, Xinpeng Ding, De Cheng, Jie Li, Nannan Wang, Xinbo Gao: ETC: Temporal Boundary Expand Then Clarify for Weakly Supervised Video Grounding With Multimodal Large Language Model. TMM, 2025.
- Runhui Huang, Xinpeng Ding, Chunwei Wang, Jianhua Han, Yulong Liu, Hengshuang Zhao, Hang Xu, Lu Hou, Wei Zhang, Xiaodan Liang: HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models. CVPR, 2025.
- Yi Li, Hualiang Wang, Xinpeng Ding, Haonan Wang, Xiaomeng Li: Token Activation Map to Visually Explain Multimodal LLMs. ICCV, 2025.
2024
- Guozhang Li, De Cheng, Xinpeng Ding, Nannan Wang, Jie Li, Xinbo Gao: Weakly Supervised Temporal Action Localization With Bidirectional Semantic Consistency Constraint. TNNLS, 2024.
- Yiqun Lin, Jiewen Yang, Hualiang Wang, Xinpeng Ding, Wei Zhao, Xiaomeng Li: C2RV: Cross-Regional and Cross-View Learning for Sparse-View CBCT Reconstruction. CVPR, 2024.
- Xinpeng Ding, Jianhua Han, Hang Xu, Xiaodan Liang, Wei Zhang, Xiaomeng Li: Holistic Autonomous Driving Understanding by Bird'View Injected Multi-Modal Large Models. CVPR, 2024.