Peixi Peng

Papers

Total Citations

H-Index

About

Peixi Peng is a leading researcher at the intersection of computer vision, medical image analysis, and robotic surgery, with a particular focus on enhancing the interpretability and intelligence of surgical AI systems. Her most notable contribution is the development of "Dual Modality Prompt Learning for Visual Question-Grounded Answering in Robotic Surgery" (2024), which addresses a critical limitation in existing visual question answering (VQA) systems. While conventional VQA models can generate textual answers, they often fail to localize the relevant content within the surgical image—a crucial capability for clinical decision-making. Peng’s work pioneers a prompt-based framework that not only answers questions but also visually grounds the response, significantly improving interpretability for surgeons. This innovation has already garnered 3 citations in its first year, signaling growing impact in the field. Her research bridges the gap between natural language understanding and spatial reasoning in high-stakes medical environments, making surgical AI more transparent and trustworthy. Peng’s work is essential reading for researchers developing explainable AI in healthcare, and her dual-modality approach sets a new standard for context-aware robotic surgery assistance.