Leichen Wang

Papers

Total Citations

H-Index

About

Leichen Wang is a rising researcher in autonomous driving perception, with a focus on neuro-symbolic reasoning and lane topology extraction. Their most-cited work, "Chameleon: Fast-Slow Neuro-Symbolic Lane Topology Extraction" (2025, 5 citations), tackles a critical challenge in mapless autonomous driving: detecting lanes and traffic elements while inferring complex relational rules, such as whether a left turn into a specific lane is feasible. By integrating fast neural processing with slow symbolic reasoning, Wang’s approach bridges the gap between data-driven perception and logical inference, enabling more robust and interpretable driving decisions. This work represents a significant step toward safer, more adaptable autonomous systems that can reason about road structures without relying on high-definition maps. Wang’s contributions are particularly notable for advancing the intersection of computer vision and symbolic AI, offering a scalable solution for real-world driving scenarios. As a young researcher, their work has already garnered attention for its innovative fusion of learning and reasoning, positioning them as a key contributor to the next generation of autonomous vehicle technology.