Litian Liang

Papers

Total Citations

H-Index

About

Litian Liang is a researcher at the intersection of robotics, natural language processing, and computer vision, with a focus on grounded language understanding and visuomotor learning. Their key contributions center on developing modular frameworks that decompose complex instruction-following tasks into interpretable components—language parsing, visual perception, and action execution—to improve data efficiency and generalization in robotic systems. Liang’s most cited work, “Modular Framework for Visuomotor Language Grounding” (2021, 5 citations), addresses the critical challenge of data scarcity in end-to-end approaches by proposing a structured pipeline that separates reasoning from control, enabling more robust and sample-efficient learning. This work has been influential in advancing grounded language robotics, offering a practical alternative to monolithic models. Liang’s research demonstrates a commitment to building transparent, modular AI systems that bridge linguistic and physical worlds, with potential applications in human-robot collaboration and autonomous navigation. Their approach has inspired further work in compositional grounding and task decomposition, marking Liang as a promising voice in the growing field of embodied AI.