Papers
1
Total Citations
18
H-Index
1
About
Yuyang Sheng is a rising researcher in computer vision and surgical robotics, with a focus on adapting foundation models for safety-critical medical applications. Their most prominent work, "Surgical-DeSAM: Decoupling SAM for Instrument Segmentation in Robotic Surgery" (2024), addresses a key limitation of the Segment Anything Model (SAM) in surgical settings—namely, the impracticality of per-frame prompts during supervised learning. By decoupling SAM’s prompt-dependent design, Sheng enables robust, automatic instrument segmentation without manual intervention, a critical step toward autonomous robotic surgery. This contribution has already garnered 18 citations in under a year, reflecting its timely impact. Sheng’s research bridges the gap between general-purpose AI and domain-specific surgical needs, tackling challenges like real-time performance and annotation efficiency. Their work is notable for pushing the boundaries of foundation model adaptability in high-stakes environments, offering a blueprint for future surgical AI systems. As an emerging voice at the intersection of deep learning and medicine, Sheng is poised to influence both academic research and clinical practice, with potential applications in minimally invasive procedures and intraoperative assistance.
Research Focus
Key Achievements
Top Papers
- 1