Wanshu Fan
Papers
1
Total Citations
3
H-Index
1
About
Wanshu Fan is advancing the frontier of intelligent robotic surgery through pioneering work in multimodal learning and visual question answering (VQA). Her research centers on developing AI systems that not only understand surgical scenes but also provide spatially grounded, interpretable responses—a critical step toward safer, more transparent robotic assistance. In her highly cited 2024 paper, "Dual modality prompt learning for visual question-grounded answering in robotic surgery," Fan introduces a novel framework that enables VQA models to localize relevant image regions while generating textual answers, addressing a key limitation of prior systems. This dual-modality approach enhances interpretability and trust in surgical AI, allowing clinicians to verify where a machine’s answer comes from. Although early in her career, her work has already garnered attention, with this paper accumulating 3 citations shortly after publication. By bridging vision and language in the high-stakes domain of robotic surgery, Fan is laying the groundwork for more interactive, accountable, and clinically useful AI assistants—an achievement that positions her as a rising innovator at the intersection of computer vision, natural language processing, and medical robotics.
Research Focus
Key Achievements
Top Papers
- 1