Papers
1
Total Citations
52
H-Index
1
About
Jing Shao is a researcher at the forefront of generative AI and medical simulation, whose work bridges the gap between advanced video generation and practical clinical training. Her most notable contribution is the development of Endora, a pioneering framework that repurposes video generation models as endoscopy simulators. This innovative approach, detailed in her 2024 paper which has already garnered 52 citations, addresses a critical need for realistic, scalable training tools in medicine. By leveraging state-of-the-art generative techniques, Shao’s work enables the creation of high-fidelity, controllable endoscopic videos without the need for expensive physical phantoms or real patient data. This breakthrough not only reduces training costs but also enhances the accessibility of surgical education. Shao’s research sits at the intersection of computer vision, generative modeling, and healthcare technology, demonstrating how cutting-edge AI can solve real-world challenges. Her impact is evident in the rapid citation of her work, signaling its immediate relevance to both the AI and medical communities. As a rising voice in this interdisciplinary field, Jing Shao is shaping the future of simulation-based learning.
Research Focus
Key Achievements
Top Papers
- 1Endora: Video Generation Models as Endoscopy Simulators52 citations · 2024