Jialang Xu
Papers
4
Total Citations
19
H-Index
3
About
Jialang Xu is a rising researcher at the forefront of surgical data science, specializing in the intersection of deep learning and robot-assisted minimally invasive surgery (RMIS). His work focuses on three critical areas: automated surgical error detection, gesture recognition, and personalized federated learning for surgical instrument segmentation. Xu’s major contributions include pioneering the "Chain-of-Gesture Prompting" method, which enhances error detection in robotic surgical videos by breaking down procedures into step-by-step gesture sequences. He also developed SEDMamba, a novel hierarchical framework that leverages selective state space modeling with bottleneck mechanisms and fine-to-coarse temporal fusion, achieving efficient long-term dependency capture for error detection. His research on personalized federated learning introduces visual trait priors, enabling multi-site collaborative training of surgical instrument segmentation models while preserving data privacy—a breakthrough for clinical deployment. With several papers accumulating early citations (6 each for his top works), Xu’s impact is rapidly growing. His notable achievements include advancing safety protocols in robotic surgery and addressing real-world challenges in surgical skill assessment and technical error mitigation, making his work highly relevant for both researchers and practitioners in surgical AI.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4