Yunzhe Wang

Papers

Total Citations

H-Index

About

Yunzhe Wang is a rising researcher at the forefront of embodied AI and reconfigurable robotics, whose work bridges the gap between large language models (LLMs), vision-language models (VLMs), and physical robotic systems. His research focuses on enabling robots to autonomously understand their own morphology and adapt their behavior accordingly—a critical step toward truly flexible, general-purpose machines. In his most-cited work, "Reconfigurable Robot Identification from Motion Data" (2024), Wang tackles the fundamental challenge of robots recognizing their own changing physical configurations using only motion data, paving the way for systems that can self-model and re-plan without human intervention. This contribution is vital for robots operating in unstructured environments where their shape or capabilities may shift. Though early in his career, Wang’s work has already garnered attention for its novel integration of multimodal AI with real-world robotic adaptation. His research promises to unlock new levels of autonomy, where robots can seamlessly interpret complex instructions and visual cues while dynamically adjusting to their own evolving hardware—a vision that positions him as a key innovator in next-generation intelligent robotics.