Modi Shi

Papers

Total Citations

H-Index

About

Modi Shi is a robotics researcher advancing the frontier of generalizable robotic manipulation. Their primary research areas include 6-DoF grasp detection, domain adaptation, and learning-based robotic perception. Shi’s most notable contribution is the work “Generalizing 6-DoF Grasp Detection via Domain Prior Knowledge” (2024), which addresses a critical limitation in modern grasp detection: the severe performance drop when models encounter unfamiliar objects or environments. By integrating domain prior knowledge, Shi’s method enables grasp detection systems to maintain robust performance across diverse, unseen scenarios—a key step toward truly autonomous robots. This work has already garnered 10 citations, signaling its early impact on the field. Shi’s research is particularly valuable for students and engineers working on real-world robotic systems, where adaptability is paramount. Their focus on generalization over memorization marks a thoughtful departure from conventional data-hungry approaches, offering a more practical path for deploying robotic grasping in unstructured settings. With this foundational contribution, Modi Shi is establishing themselves as a rising voice in the quest for more intelligent and adaptable robotic hands.