I am a Master's student at the School of Computer Science and Technology, East China Normal University (ECNU), supervised by Prof. Changbo Wang and Assoc. Prof. Yang Li. My research interests include video content understanding, multimodal large models, vision foundation models, and computer vision. Currently, my work focuses on streaming video understanding, memory management mechanisms in vision-language models, and multi-task training for vision-language models.
Before joining ECNU, I received my B.S. in Computer Science and Technology from Huazhong Agricultural University. During my undergraduate years, I was an active competitive programmer and won awards in multiple national programming contests. In addition, I have full-stack AI system development experience spanning from prototype to deployment, applying computer vision to real-world scenarios such as psychological assessment and industrial systems.
If you are interested in my work, feel free to reach out via email!

Chenxi Shao, Bozhong Wang, Jiaxin Huang, Zhao Liu, Sunwei Zhu, Tianxin Hang, Gaoqi He, Yang Li#, Changbo Wang# (# corresponding author)
arXiv preprint Aug. 2026
We present StreamSoccer, an event-driven system for causal streaming soccer commentary. It maintains fixed-budget event memory, preserves completed events as local context, and consolidates them into retrievable historical records for current-event, recent-window, and historical-memory commentary.
Chenxi Shao, Bozhong Wang, Jiaxin Huang, Zhao Liu, Sunwei Zhu, Tianxin Hang, Gaoqi He, Yang Li#, Changbo Wang# (# corresponding author)
arXiv preprint Aug. 2026
We present StreamSoccer, an event-driven system for causal streaming soccer commentary. It maintains fixed-budget event memory, preserves completed events as local context, and consolidates them into retrievable historical records for current-event, recent-window, and historical-memory commentary.

Yuxuan Cheng, Chenxi Shao, Jie Ma, Yunfei Xie, Guoliang Li
arXiv preprint Oct. 2024
Medical image segmentation relies on high-quality annotated data that is often difficult and costly to obtain. To address this, we propose an Attention-Guided weak-to-Strong Consistency Match (AIGCMatch) framework that incorporates attention-guided perturbation strategies at both the image level and feature level to achieve weak-to-strong consistency regularization. This approach preserves the structural information of medical images while enhancing the model's ability to process complex semantic information. Extensive experiments on the ACDC and ISIC-2017 datasets validate the effectiveness of our method, achieving a 90.4% Dice score on ACDC in the 7-case scenario and significantly outperforming baselines on ISIC-2017.
Yuxuan Cheng, Chenxi Shao, Jie Ma, Yunfei Xie, Guoliang Li
arXiv preprint Oct. 2024
Medical image segmentation relies on high-quality annotated data that is often difficult and costly to obtain. To address this, we propose an Attention-Guided weak-to-Strong Consistency Match (AIGCMatch) framework that incorporates attention-guided perturbation strategies at both the image level and feature level to achieve weak-to-strong consistency regularization. This approach preserves the structural information of medical images while enhancing the model's ability to process complex semantic information. Extensive experiments on the ACDC and ISIC-2017 datasets validate the effectiveness of our method, achieving a 90.4% Dice score on ACDC in the 7-case scenario and significantly outperforming baselines on ISIC-2017.