Papers
1
Total Citations
18
H-Index
1
About
Yefei Wang is a researcher at the forefront of multimodal perception and robotic manipulation, with a particular focus on integrating audio and visual cues to enhance human-robot interaction. His most cited work, "Audio-Visual Grounding Referring Expression for Robotic Manipulation" (2022, 18 citations), introduces a novel task that enables robots to interpret referring expressions by simultaneously processing auditory and visual information. This contribution addresses a critical gap in natural language understanding for robotics, moving beyond traditional vision-only approaches to incorporate sound as a grounding modality. Wang's research is pivotal in developing more intuitive and context-aware robotic systems, allowing machines to better comprehend ambiguous or complex instructions in dynamic environments. By pioneering the fusion of audio-visual grounding with robotic manipulation, his work has laid the groundwork for more sophisticated, human-like interaction in assistive and industrial robotics. With growing citation impact, Wang is recognized for advancing the intersection of perception, language, and action, making his research essential reading for those interested in embodied AI and multimodal learning.
Research Focus
Key Achievements
Top Papers
- 1Audio-Visual Grounding Referring Expression for Robotic Manipulation18 citations · 2022