I am Yunjiang Xu (徐云江), a PhD student at City University of Hong Kong, supervised by Prof. Jianping Wang and Prof. Qian Zhou. I received my M.S. degree from Soochow University in 2025, supervised by Prof. Jin Wang and Prof. Lingzhi Li.
My research interests include autonomous driving, collaborative perception, embodied intelligence, and unsupervised learning. I focus on making perception systems robust in real-world multi-agent settings — handling asynchrony, bandwidth constraints, and occlusion through principled feature-level fusion.
For collaboration or academic exchange, please feel free to reach out via email.
Collaborative perception systems overcome single-vehicle limitations in long-range detection and occlusion scenarios by integrating multi-agent sensory data, improving accuracy and safety. However, frequent cooperative interactions and real-time requirements impose stringent bandwidth constraints. Previous works prove that query-based instance-level interaction reduces bandwidth demands and manual priors, however, LiDAR-focused implementations in collaborative perception remain underdeveloped, with performance still trailing state-of-the-art approaches. To bridge this gap, we propose INSTINCT (instance-level interaction architecture), a novel collaborative perception framework featuring three core components: (1) a quality-aware filtering mechanism for high-quality instance feature selection; (2) a dual-branch detection routing scheme to decouple collaboration-irrelevant and collaboration-relevant instances; (3) a Cross Agent Local Instance Fusion module to aggregate local hybrid instance features. Additionally, we enhance the ground truth (GT) sampling technique to facilitate training with diverse hybrid instance features. Extensive experiments across multiple datasets demonstrate that INSTINCT achieves superior performance. Specifically, our method achieves an improvement in accuracy 13.23%/32.24% in DAIR-V2X and V2V4Real while reducing the communication bandwidth to 1/281 and 1/264 compared to state-of-the-art methods.
@inproceedings{xu2025instinct,title={INSTINCT: Instance-Level Interaction Architecture for Query-Based Collaborative Perception},author={Xu, Yunjiang and Li, Lingzhi and Wang, Jin and Ouyang, Yupeng and Yang, Benyuan},booktitle={IEEE/CVF International Conference on Computer Vision},year={2025},}
ICRA
CoDynTrust: Robust Asynchronous Collaborative Perception via Dynamic Feature Trust Modulus
Yunjiang Xu, Lingzhi Li, Jin Wang, and 4 more authors
In IEEE International Conference on Robotics and Automation, 2025
Collaborative perception, fusing information from multiple agents, can extend perception range so as to improve perception performance. However, temporal asynchrony in real-world environments, caused by communication delays, clock misalignment, or sampling configuration differences, can lead to information mismatches. To tackle this challenge, we propose CoDynTrust, an uncertainty-encoded asynchronous fusion perception framework that is robust to the information mismatches caused by temporal asynchrony. CoDynTrust generates dynamic feature trust modulus (DFTM) for each region of interest by modeling aleatoric and epistemic uncertainty as well as selectively suppressing or retaining single-vehicle features, thereby mitigating information mismatches. We then design a multi-scale fusion module to handle multi-scale feature maps processed by DFTM. Experimental results demonstrate that CoDynTrust significantly reduces performance degradation caused by temporal asynchrony across multiple datasets, achieving state-of-the-art detection performance even with temporal asynchrony.
@inproceedings{xu2025codyntrust,title={CoDynTrust: Robust Asynchronous Collaborative Perception via Dynamic Feature Trust Modulus},author={Xu, Yunjiang and Li, Lingzhi and Wang, Jin and Yang, Benyuan and Wu, Zhiwen and Chen, Xinhong and Wang, Jianping},booktitle={IEEE International Conference on Robotics and Automation},year={2025},}
