Guanjin Wang

Murdoch University, University of Maryland, College Park, University of Mary

Papers

Total Citations

H-Index

About

Guanjin Wang is a researcher whose work bridges the cutting edge of artificial intelligence and robotics, with a particular focus on how machines perceive and interact with complex, real-world environments. His research spans two key areas: multi-modal large language models (LLMs) and the mechanics of robotic locomotion on deformable terrain. In his most notable contribution, a 2025 systematic review on multi-modal LLMs, Wang critically analyzed how these models integrate visual and audio data to overcome the limitations of text-only systems, providing a foundational roadmap for domain-specific applications. This work has already garnered 5 citations, signaling its growing influence in the AI community. Earlier, Wang made significant strides in robotics through computational studies on robot leg interactions with granular and soft terrain. His 2020 paper on continuum modeling of robotic appendages in granular material, along with his 2017 study on deformable terrain interactions, tackled the challenge of large deformations and plastic flows using advanced simulation techniques. These contributions, with 5 and 4 citations respectively, are essential for advancing legged locomotion in natural environments. Wang’s work uniquely positions him at the intersection of AI perception and physical robotics, offering critical insights for students and researchers developing autonomous systems that must navigate and understand the messy, multi-modal world.