Yu-Siang Wang
Papers
2
Total Citations
16
H-Index
2
About
Yu-Siang Wang is a researcher working at the intersection of robotics, computer vision, and natural language processing, with a particular focus on visual grounding in real-world environments. His most notable contribution is the development of OCID-Ref, a pioneering 3D robotic dataset that pairs embodied language with cluttered scene data to advance visual grounding capabilities in robotic systems. This work addresses a critical gap in the field: enabling robots to accurately identify and interact with occluded objects in practical working environments such as offices and warehouses — settings where reliable object recognition is essential for human-robot collaboration. Published at the prestigious NAACL 2021 conference, OCID-Ref has garnered 14 citations, reflecting its value to the research community as a benchmark resource for evaluating and improving machine perception in complex scenes. Wang's work bridges the divide between language understanding and spatial reasoning, pushing forward the development of robots that can respond meaningfully to natural language instructions even when visual scenes are cluttered and challenging. For students and researchers exploring embodied AI, robotic perception, or referring expression comprehension, Wang's contributions offer a foundational dataset and framework for tackling some of the field's most demanding real-world challenges.
Research Focus
Key Achievements
Top Papers
- 1
- 2