Congcong Wen
Papers
2
Total Citations
5
H-Index
2
About
Congcong Wen is a researcher at the forefront of robotics and artificial intelligence, specializing in the security and reliability of autonomous navigation systems. Her work critically examines the vulnerabilities of Large Language Model (LLM)-based navigation in urban environments, a pioneering contribution that addresses a crucial gap in the field. In her 2024 paper, "How Secure Are Large Language Models (LLMs) for Navigation in Urban Environments?" (3 citations), she systematically uncovers security flaws that could compromise autonomous systems, setting a new agenda for safe AI deployment. Wen further advances the field by investigating the reliability of foundation models in zero-shot object goal navigation, as detailed in her 2024 work (2 citations), which explores how these models can be trusted for frontier selection without prior training. Her research not only highlights critical risks but also proposes pathways to more robust and dependable AI-driven navigation. By bridging security and reliability, Wen’s work is essential for students and researchers aiming to build trustworthy autonomous systems that can operate safely in complex, real-world environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2