Dongwoo Nam

Gwangju Institute of Science and Technology

Papers

Total Citations

H-Index

About

Dongwoo Nam is a researcher at the forefront of robotic manipulation and computer vision, with a primary focus on bridging the gap between large-scale vision models and practical grasp detection. His most notable contribution is the introduction of GraspSAM, a pioneering extension of the Segment Anything Model (SAM) that enables prompt-driven, category-agnostic grasp detection. This work, published in 2025, has already garnered 6 citations, reflecting its immediate impact on the field. By allowing users to guide grasp generation through intuitive prompts—such as points or bounding boxes—Nam’s approach eliminates the need for prior object knowledge, making robotic grasping more flexible and user-friendly. This innovation is particularly significant for applications in unstructured environments, where objects vary widely in shape and context. Nam’s research stands out for its elegant integration of foundation models with robotic tasks, offering a new paradigm for interactive and adaptive manipulation. His work not only advances the state of the art in grasp detection but also opens avenues for more intuitive human-robot collaboration, marking him as a promising young researcher in embodied AI and robotics.