I am Shuchang Lyu. I work on computer vision and pattern recognition, remote sensing image analysis and mllm-based downstream task.

Currently, I am working as a Lecturer in the School of Artificial Intelligence at University of Science and Technology Beijing (USTB). I work in Machine Vision and Intelligent Perception Team leading by Prof. Hongmin Liu. In this wonderful team, I am working closely with Prof. Bin Fan. Under his guidance and through our close collaboration, I have the opportunity to contribute to joint research and to help mentor students. I was a Postdoctoral Researcher (“Outstanding Postdoc Series”) at Beihang University (BUAA) guided by Prof. Zhenwei Shi.

I obtained my PhD degree from Beihang University (BUAA) in June 2024. Prior to that, I worked as a Research Intern / Algorithm Engineer in the Autonomous Driving Group at SenseTime from 2019 to 2020, mentored by Prof. Guangliang Cheng.

My research has received nearly 5,000 citations on Google Scholar. I am also an IEEE Senior Member.

My current research focuses on the following key areas:

• Multimodal Large-Language Models (MLLMs) for downstream tasks: Step-by-step cognitive reasoning, multi-entity grounding, and advancing from passive matching perception to explicit visual reasoning/thinking.
• Remote Sensing Image Analysis: Domain adaptation/generalization in Remote Sensing, visible-thermal tiny object detection, and remote sensing visual grounding/referring segmentation.

I serve as a regular reviewer for top-tier international journals and conferences, including AAAI, ACMMM, IEEE-TCSVT, IEEE-TGRS, ISPRS, …