SearcharxivSearch

arXiv subjects

Qiaoran Wang

Publications and source records attributed to Qiaoran Wang.

3 recordsLinked to original sources

SpatialPrompt: XR-Based Spatial Intent Expression as Executable Constraints for AI Generative 3D Design

We present SpatialPrompt, an Extended Reality(XR) system that turns spatial sketches into executable constraints for controllable 3D generation. Users draw rough structures with a 3D pen and add voice prompts for semantic and stylistic intent. The system supports iterative refinement and synchronous co-creation in shared space with color-coded contributions. Implemented on Apple Vision Pro with Logitech Muse and Meshy, a heuristic evaluation suggests that the workflow is intuitive and supports shared understanding in collaborative creation, while revealing needs for faster generation and clearer feedback.

cs.HC

NieNie: Adaptive Rhythmic System for Stress Relief with LLM-Based Guidance

Today's young people are facing increasing psychological stress due to various social issues. Traditional stress management tools often rely on static scripts or passive content, which are ineffective in alleviating stress. NieNie addresses this gap by combining rhythm biofeedback with real-time psychological guidance through a large language model (LLM), offering an interactive, tactile response. The system is specifically designed for young people experiencing emotional stress, collecting physiological signals such as heart rate variability and generating adaptive squeeze-release rhythms via soft, tactile devices. Utilising LLM, the system provides timely squeezing rhythms and psychologically guided feedback prompts, offering personalised rhythm games while reinforcing stress restructuring. Unlike traditional mental health apps, NieNie places users within an embodied interactive loop, leveraging tactile interaction, biofeedback, and adaptive language support to create an immersive stress regulation experience. This study demonstrates how embodied systems can connect bodily actions with mental health in everyday contexts.

cs.HC

MeloKids: Multisensory VR System to Enhance Speech and Motor Coordination in Children with Hearing Loss

Children with hearing impairments face ongoing challenges in language and motor development. This study explores how multi-sensory feedback technology based on virtual reality (VR), integrating auditory, visual, and tactile stimuli, can enhance rehabilitation outcomes. Using functional near-infrared spectroscopy (fNIRS) technology, we assessed cortical activation patterns in children during pitch-matching tasks across different interaction modes. Our findings aim to provide evidence for designing personalized, interactive rehabilitation systems that enhance cognitive engagement and motor control in children with hearing impairments.

cs.HC