Hengxu Li
Papers
1
Total Citations
2
H-Index
1
About
Hengxu Li is a researcher at the intersection of robotics, cognitive science, and artificial intelligence, with a focus on bridging the gap between data-driven models and structured reasoning. His key research areas include vision-language-action (VLA) models, cognitive architectures, and symbolic state representation for autonomous systems. Li’s most notable contribution is his pioneering work on probing VLA models to extract symbolic states and integrating them into cognitive architectures—a novel approach that aims to combine the flexibility of deep learning with the reliability of symbolic reasoning. This work, published in 2025 and already garnering 2 citations, addresses a critical limitation of VLA models: their black-box nature and sensitivity to environmental changes. By enabling these models to interface with cognitive architectures, Li proposes a pathway toward more robust, interpretable, and generalizable robotic systems. His research is particularly impactful for students and researchers interested in neuro-symbolic AI, human-robot interaction, and the future of autonomous agents. Li’s work stands out for its ambition to reconcile two often-disparate paradigms, offering a concrete methodology for building AI systems that are both powerful and trustworthy.
Research Focus
Key Achievements
Top Papers
- 1