Hi, I’m Jinrong Zhang (张津榕) 👋
Ph.D. student in Electronic Information at Harbin Institute of Technology, Shenzhen, supervised by Prof. Jianlong Wu.
My research interests focus on Multimodal Large Language Models, Multimodal Reasoning, Open-World Object Detection & Segmentation, and Video Understanding & Temporal Analysis.
📖 Education
| Period | University | Degree |
|---|---|---|
| 2025.09 - 2029.06 | Harbin Institute of Technology, Shenzhen | PhD in Electronic Information |
| 2022.09 - 2025.06 | Dalian University of Technology | Master in Control Science and Engineering |
| 2018.09 - 2022.06 | Dalian University of Technology | Bachelor in Transportation Engineering |
💻 Experience
- Research Intern, Xiaomi (2024.03 - 2024.09)
- Open-world detection & segmentation for defect detection at Xiaomi Automobile Factory. Outperformed SAM2 with +4.6% AP50 and >30% boost on long-tail categories.
- CVPR Workshop, 5th PVUW Challenge (2026.02 - 2026.03)
- 1st Place, 5th MOSE Challenge — Outperformed 2nd place by 1.75% J&F
- 1st Place, 5th MeViS-Text Challenge — Outperformed 2nd place by 7.91% J&F
📝 Selected Publications
* Equal contribution # Corresponding author
-
[CVPR 2026] Breaking the Regional Perception Bottleneck of MLLMs via External Reasoning Framework Jinrong Zhang, Zhaoyang Xu, Xusheng He, Xinrui Li, Na Zheng, Jianlong Wu#
-
[AAAI 2025] Just a Few Glances: Open-Set Visual Perception with Image Prompt Paradigm Jinrong Zhang, Penghui Wang, Chunxiao Liu, Wei Liu, Dian Jin, Qiong Zhang#, Erli Meng#, Zhengnan Hu
-
[CVPR 2025] DTOS: Dynamic Time Object Sensing with Large Multimodal Model Jirui Tian*, Jinrong Zhang*, Shenglan Liu#, Luhao Xu, Zhixiong Huang, Gao Huang
-
[TNNLS 2025] End-to-End Streaming Video Temporal Action Segmentation With Reinforcement Learning JinRong Zhang, WuJun Wen, ShengLan Liu, Gao Huang, YunHeng Li, QiFeng Li, Lin Feng#
-
[ICME 2025] Flexible Streaming Temporal Action Segmentation with Diffusion Models Jinrong Zhang, Wujun Wen, Shenglan Liu, Sifan Zhang, Yuning Ding, Lin Feng#
More Publications
- **[TNNLS 2024]** [Multidimensional Refinement Graph Convolutional Network with Robust Decouple Loss for Fine-Grained Skeleton-Based Action Recognition](https://ieeexplore.ieee.org/abstract/document/10499829/) Sheng-Lan Liu, Yu-Ning Ding, **Jin-Rong Zhang**, et al. - **[ACM MM 2024]** [2M-AF: A Strong Multi-Modality Framework for Human Action Quality Assessment with Self-Supervised Representation Learning](https://dl.acm.org/doi/abs/10.1145/3664647.3681084) Yuning Ding, Sifan Zhang, Liu Shenglan, **Jinrong Zhang**, et al. - **[ICASSP 2025]** [Cluster-Refined Optimal Transport for Unsupervised Action Segmentation](https://ieeexplore.ieee.org/document/10887693) Shijie Wang\*, **Jinrong Zhang**\*, et al. - **[IJCNN 2025]** [Unsupervised Temporal Action Segmentation Based on Wavelet Feature Processing](https://ieeexplore.ieee.org/document/11229403) Xianghan Lin\*, **Jinrong Zhang**\*, et al.🎖 Achievements
- Outstanding Graduate, Dalian University of Technology
- International Underwater Robot Competition, Championship
- The 19th RoboMaster Robotics Competition, Second Prize
- China Robotics Competition (Underwater Robot Operations Project), Second Prize
- Chinese Collegiate Computing Competition, Second Prize