Daeyun Shin

Papers

Total Citations

H-Index

About

Daeyun Shin is a researcher advancing the integration of vision, language, and robotics through modular and data-efficient frameworks. His key contributions lie in visuomotor language grounding—teaching machines to follow natural language instructions by linking perception, comprehension, and action. In his highly cited work, "Modular Framework for Visuomotor Language Grounding" (2021), Shin tackles the critical challenge of data inefficiency in end-to-end robotic learning. Rather than relying on expensive, monolithic datasets, he proposes structuring language, acting, and visual tasks into discrete, reusable modules. This approach not only reduces the need for massive training data but also enhances interpretability and transferability across different robotic tasks. With 5 citations, this work has already sparked interest in more efficient grounded language systems. Shin’s research is particularly impactful for students and researchers working at the intersection of natural language processing, computer vision, and robotics, offering a pragmatic path toward scalable, instruction-following agents. His modular methodology stands as a notable achievement, promising to accelerate progress in real-world human-robot interaction.