Liejun Wang
Papers
1
Total Citations
2
H-Index
1
About
Liejun Wang is a leading researcher in embodied artificial intelligence, with a primary focus on audio-visual navigation—a cutting-edge domain that trains robots to locate sound-emitting targets using egocentric visual and auditory inputs. His most cited work, “Pay Self-Attention to Audio-Visual Navigation” (2022, 2 citations), introduces a novel self-attention mechanism for fusing multimodal sensory data, significantly improving how robots interpret and act upon simultaneous visual scenes and directional audio cues. This contribution addresses a critical bottleneck in embodied AI: the effective integration of heterogeneous sensor streams for real-world navigation. Wang’s research advances the theoretical understanding of cross-modal attention while offering practical frameworks for deploying autonomous systems in complex, dynamic environments. Though early in its citation trajectory, his work is foundational for next-generation robotics, particularly in search-and-rescue, assistive technology, and human-robot interaction. By bridging audio perception with visual planning, Wang is shaping how machines perceive and move through the world, marking him as a rising innovator in embodied AI research.
Research Focus
Key Achievements
Top Papers
- 1Pay Self-Attention to Audio-Visual Navigation2 citations · 2022