Tieyong Zeng
Papers
1
Total Citations
2
H-Index
1
About
Tieyong Zeng is a pioneering researcher at the intersection of computer vision, medical robotics, and artificial intelligence, with a primary focus on advancing autonomous systems for endoscopic procedures. His most notable contribution is the development of EndoVLA, a dual-phase vision-language-action model that enables autonomous tracking of abnormal regions and circumferential cutting markers during endoscopy. This groundbreaking work addresses a critical challenge in gastrointestinal interventions by reducing the cognitive burden on endoscopists through intelligent, real-time navigation. Unlike conventional model-based pipelines that require manual calibration for each component—such as detection and motion planning—Zeng’s approach integrates vision and language understanding to create a more robust and adaptive system. While his work has already garnered early citations, its potential impact on surgical robotics and minimally invasive medicine is substantial. Zeng’s research represents a significant step toward fully autonomous endoscopic systems, promising to enhance procedural accuracy and reduce operator fatigue. His innovative fusion of vision-language models with action planning places him at the forefront of next-generation medical AI, with implications for improving patient outcomes and standardizing complex endoscopic techniques.
Research Focus
Key Achievements
Top Papers
- 1