Zining Wang
Papers
1
Total Citations
13
H-Index
1
About
Zining Wang is an emerging researcher at the intersection of human-robot interaction, social robotics, and artificial intelligence, with a particular focus on leveraging large language models (LLMs) to enhance the expressiveness and naturalness of robot behavior. Their most notable work, "Ain't Misbehavin'," published in 2024 and already accumulating 13 citations, tackles one of the central challenges in social robotics: moving beyond rigid, scripted conversational systems toward more dynamic, contextually aware interactions. By integrating LLMs into the tabletop robot Haru's conversational framework, Wang and collaborators demonstrated a promising pathway for robots to establish more authentic and sustained long-term relationships with human users. This contribution is particularly significant given the growing demand for socially intelligent robots in settings such as education, healthcare, and companionship. Wang's research speaks directly to a critical gap in the field — bridging sophisticated AI language capabilities with embodied robotic expression — positioning their work as a meaningful stepping stone toward robots that can genuinely engage, adapt, and connect with the people they interact with.
Research Focus
Key Achievements
Top Papers
- 1