Xingguo Huang
Papers
1
Total Citations
17
H-Index
1
About
Xingguo Huang is a rising researcher in embodied AI, with a primary focus on Embodied Question Answering (EQA)—a field where agents must actively explore environments to answer user questions. His most cited work, "Robust-EQA: Robust Learning for Embodied Question Answering With Noisy Labels" (2023, 17 citations), tackles a critical yet underexplored challenge: learning from imperfect, noisy data in real-world scenarios. By developing robust training techniques, Huang has helped bridge the gap between controlled lab settings and practical deployment, where labels are often unreliable. This contribution is foundational for advancing EQA's potential in applications like autonomous navigation, assistive robotics, and human-robot interaction. Though early in his career, Huang’s work signals a deep commitment to making embodied agents more resilient and trustworthy. His research not only pushes the boundaries of interactive AI but also addresses the practical hurdles that limit real-world adoption, marking him as a promising voice in the next generation of embodied intelligence researchers.
Research Focus
Key Achievements
Top Papers
- 1