Yun-Hsuan Liu
Papers
2
Total Citations
16
H-Index
2
About
Yun-Hsuan Liu is a researcher working at the intersection of robotics, computer vision, and natural language processing, with a particular focus on embodied AI and visual grounding in real-world environments. Their most notable contribution is the development of OCID-Ref, a pioneering 3D robotic dataset that pairs embodied language with cluttered scene understanding, designed to advance how robots perceive and interact with partially occluded objects in practical settings such as offices and warehouses. This work, published at the prestigious 2021 NAACL conference, addresses a critical gap in visual grounding research by providing a benchmark specifically tailored to robotic working environments — a challenge largely overlooked by prior datasets. Collaborated with researchers including Winston Hsu and Wen-Chin Chen, the OCID-Ref dataset has garnered 14 citations, reflecting meaningful early traction within the embodied AI and human-robot interaction communities. Liu's research speaks to a broader mission of making robots more capable of understanding natural language instructions in complex, realistic scenes — a foundational step toward deploying intelligent robotic assistants that can reliably assist humans in everyday environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2