Ziliang Xiong
Papers
1
Total Citations
19
H-Index
1
About
Ziliang Xiong is a researcher advancing the reliability and safety of deep learning in physical systems, with a primary focus on uncertainty quantification for robotic and autonomous applications. His most-cited work, "Uncertainty Quantification Metrics for Deep Regression" (2024, 19 citations), addresses a critical gap in deploying deep neural networks on robots and other real-world systems: ensuring that learned models can reliably quantify predictive uncertainty. This capability is essential for downstream modules to reason about the safety of their actions, making his contributions vital for trustworthy AI in high-stakes environments. Xiong’s research bridges the gap between theoretical robustness and practical deployment, offering metrics that enable safer decision-making in robotics. His work has already garnered attention for its direct impact on reliable AI systems, and he continues to push boundaries in making deep learning more accountable and interpretable in physical contexts. For students and researchers, Xiong’s research exemplifies how rigorous uncertainty quantification can transform neural networks from black boxes into dependable partners in automation and control.
Research Focus
Key Achievements
Top Papers
- 1Uncertainty quantification metrics for deep regression19 citations · 2024