Siyu Zha’s research while affiliated with Tsinghua University and other places

Block-building activities are crucial for developing children's spatial reasoning and mathematical skills, yet parents often lack the expertise to guide these activities effectively. BrickSmart, a pioneering system, addresses this gap by providing spatial language guidance through a structured three-step process: Discovery & Design, Build & Learn, and Explore & Expand. This system uniquely supports parents in 1) generating personalized block-building instructions, 2) guiding parents to teach spatial language during building and interactive play, and 3) tracking children's learning progress, altogether enhancing children's engagement and cognitive development. In a comparative study involving 12 parent-child pairs children aged 6-8 years) for both experimental and control groups, BrickSmart demonstrated improvements in supportiveness, efficiency, and innovation, with a significant increase in children's use of spatial vocabularies during block play, thereby offering an effective framework for fostering spatial language skills in children.

As immersive social platforms like VRChat increasingly adopt gen-erative AI (GenAI) technologies, it becomes critical to understand how community members perceive, negotiate, and utilize these tools. In this preliminary study, we conducted a qualitative analysis of VRChat-related Discord discussions, employing a deductive coding framework to identify key themes related to AI-assisted content creation, intellectual property disputes, and evolving community norms. Our findings offer preliminary insights into the complex interplay between the community's enthusiasm for AI-driven creativity and deep-rooted ethical and legal concerns. Users weigh issues of fair use, data ethics, intellectual property, and the role of community governance in establishing trust. By highlighting the tensions and trade-offs as users embrace new creative opportunities while seeking transparency, fair attribution, and equitable policies, this research offers valuable insights for designers, platform administrators, and policymakers aiming to foster responsible, inclusive, and ethically sound AI integration in future immersive virtual environments. CCS Concepts • Human-centered computing → Empirical studies in collaborative and social computing; Empirical studies in HCI.

Online collaborative learning and working are important for everyone including children. However, children still face a lot of difficulties communicating and working together while online, which keeps them from engaging in long-term project-based teamwork. We aim to investigate online long-term collaborative learning opportunities to address this gap. We design COLP, an online, 16-week, project-based learning program, as an educational intervention based on multiple learning theories for primary school students. We conducted this program with 67 primary school students ages 8-13, across more than five provinces of China. We found that this program could engage more than one-third of children in teamwork after long-term study. Furthermore, we interview children and their parents to help us understand the communication channel, benefits, and challenges of this program. Interestingly, we discovered that parents play multiple roles in their children's collaborative learning, particularly modeling and guiding the children's collaborative skills. Given the lack of programs designed for children's long-term online collaboration, this study may inspire intervention design in computer-supported collaborative learning communities.

With the increasing integration of large lauguage models (LLMs) in education, there is growing interest in using AI agents to support student learning in creative tasks. This study presents an interactive Mentor Agent system named Mentigo, which is designed to assist middle school students in the creative problem solving (CPS) process. We created a comprehensive dataset of real classroom interactions between students and mentors, which include the structured CPS task management, diverse guidance techniques, personalized feedback mechanisms. Based on this dataset, we create agentic workflow for the Mentigo system. The system's effectiveness was evaluated through a comparative experiment with 12 students and reviewed by five expert teachers. The Mentigo system demonstrated significant improvements in student engagement and creative outcomes. The findings provide design implications for leveraging LLMs to support CPS and offer insights into the application of AI mentor agents in educational contexts.

Deep learning technology can improve sensing efficiency and has the ability to discover potential patterns in data; the efficiency of user behavior recognition in the field of smart homes has been further improved, making the recognition process more intelligent and humanized. This paper analyzes the optical sensors commonly used in smart homes and their working principles through case studies and explores the technical framework of user behavior recognition based on optical sensors. At the same time, CiteSpace (Basic version 6.2.R6) software is used to visualize and analyze the related literature, elaborate the main research hotspots and evolutionary changes of optical sensor-based smart home user behavior recognition, and summarize the future research trends. Finally, fully utilizing the advantages of cloud computing technology, such as scalability and on-demand services, combining typical life situations and the requirements of smart home users, a smart home data collection and processing technology framework based on elderly fall monitoring scenarios is designed. Based on the comprehensive research results, the application and positive impact of optical sensors in smart home user behavior recognition were analyzed, and inspiration was provided for future smart home user experience research.

In this paper, we present HoloBoard, an interactive large-format pseudo-holographic display system for lecture-based classes. With its unique properties of immersive visual display and transparent screen, we designed and implemented a rich set of novel interaction techniques like immersive presentation, role-play, and lecturing behind the scene that is potentially valuable for lecturing in class. We conducted a controlled experimental study to compare a HoloBoard class with a normal class by measuring students' learning outcomes and three dimensions of engagement (i.e., behavioral, emotional, and cognitive engagement). We used pre-/post- knowledge tests and multimodal learning analytics to measure students' learning outcomes and learning experiences. Results indicated that the lecture-based class utilizing HoloBoard lead to slightly better learning outcomes and a significantly higher level of student engagement. Given the results, we discussed the impact of HoloBoard as an immersive media in the classroom setting and suggest several design implications for deploying HoloBoard in immersive teaching practices.