Brian Liang
Papers
1
Total Citations
2
H-Index
1
About
Brian Liang is a rising researcher at the forefront of human-robot interaction and embodied AI, with a focus on bridging the gap between complex robotic systems and natural human communication. His work centers on enabling robots to articulate their own experiences and decision-making processes in real-world contexts, a critical step toward transparency and trust in autonomous systems. Liang’s most cited paper, “I Can Tell What I am Doing: Toward Real-World Natural Language Grounding of Robot Experiences” (2024, 2 citations), introduces a novel framework that leverages large language models (LLMs) to translate multi-modal robotic data—such as sensor inputs and action sequences—into coherent, human-readable narratives. This contribution directly addresses the challenge of making robot behaviors interpretable, paving the way for more intuitive human-robot collaboration. Though early in his career, Liang’s work has already garnered attention for its practical implications in fields like assistive robotics and autonomous navigation. His research stands out for its emphasis on real-world grounding, moving beyond simulated environments to tackle the messiness of physical interaction. As LLMs continue to reshape AI, Liang’s approach offers a promising path toward robots that can not only act but also explain themselves.
Research Focus
Key Achievements
Top Papers
- 1