Junrong Song

Junrong Song

Auto-generated profile, based on publicly available information

Junrong Song

The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

7 March 2026
Verified
Conference Paper
Open access
YGYinghao Gao
Yinghao Gao
YYYongbo Yang
Yongbo Yang
CZChenwan Halley Zhong
Chenwan Halley Zhong
XZXinyi Zhang
Xinyi Zhang
JSJunrong Song
Junrong Song
XTXin Tong
Xin Tong
We present RoboTheater, a multi-robot storytelling platform, designed to explore and demonstrate the expressive capabilities of robots in stage execution. RoboTheater bridges computational narrative generation with embodied robotic execution, enabling robots to perform with varied dialogues and movements to create immersive stage narratives. The system uses large language models (LLMs) to generate structured scripts that are mapped into robots’ movements, speech, and visual projections, with all commands sent over a wireless network. A user study with 13 participants was conducted to evaluate the system’s usability and gather feedback. Our findings indicate that the RoboTheater effectively conveys emotion and character through multimodal cues, sustaining audience engagement and immersion. The work expands multi-robot storytelling and paves the way for creative, narrative applications.



13 June 2026
Verified
Conference Paper
Open access
JSJunrong Song
Junrong Song
HWHuanyi Wan
Huanyi Wan
LHLei Han
Lei Han
YGYinghao Gao
Yinghao Gao
DYDavid Yip
David Yip
XTXin Tong
Xin Tong
We present CoStage, an AI-supported embodied co-creation platform that combines LLM-based story generation with multi-robot stage performance to support children’s narrative construction and spatial imagination. Unlike prior AI storytelling tools that are largely screen-based, CoStage allows children to direct robot actors on a 360° tangible stage, transforming written stories into spatially enacted performances. Informed by formative work with domain experts, we evaluated CoStage in a within-subjects study (N = 24) comparing a robot enactment condition with a screen-based animation condition. Our findings indicate that robot-stage performance can heighten immersion, strengthen children’s sense of directorial agency, support spatial sensemaking, and foster a planning–enactment coordination loop during storytelling. This work advances child–computer interaction by offering design implications and demonstrating how embodied AI co-creation can support children’s spatial cognition and narrative engagement.