Hu Kuang

Papers

Total Citations

H-Index

About

Hu Kuang is a rising researcher at the forefront of robotic manipulation and embodied AI, with a focus on bridging vision, language, and physical interaction. His most cited work introduces a pioneering two-tier grasp pose detection architecture that leverages vision-language models to infer not just where, but *how* a robot should grasp an object based on its semantic functionality and physical attributes. This approach overcomes a critical limitation of traditional deep learning methods, which often ignore object semantics. While his career is in its early stages, this 2025 paper has already garnered attention for its novel integration of language priors into grasp planning—a key step toward robots that can understand and act on human intent. Kuang’s work sits at the intersection of computer vision, natural language processing, and robotics, promising more intuitive and adaptable automation. As the field moves toward generalist robots, his contributions offer a compelling blueprint for machines that see, reason, and grasp with human-like awareness.