Mentigo: An Intelligent Agent for Mentoring Students in the Creative Problem Solving ProcessCreative Problem-Solving (CPS) promotes creative and critical thinking while enhancing real-world problem-solving skills, making it essential for middle school education. However, providing personalized mentorship in CPS projects at scale is challenging due to resource constraints and diverse student needs. To address this, we developed Mentigo, an AI-driven mentor agent designed to guide middle school students through the CPS process. Using a dataset of real classroom interactions, we encoded CPS task stages, adaptive guidance strategies, and personalized feedback mechanisms to inform Mentigo`s dynamic mentoring framework powered by large language models (LLMs). A comparative experiment with 12 students and evaluations from five expert educators demonstrated improved student engagement, creativity, and task performance. Our findings highlight design implications for using LLM-based AI mentors to enhance CPS learning in educational environments.2025SZSiyu Zha et al.Tsinghua UniversityHuman-LLM CollaborationIntelligent Tutoring Systems & Learning AnalyticsCHI
Slip-Grip: An Electrotactile Method to Simulate WeightWeight perception is crucial for immersive virtual reality (VR) interactions, yet providing weight feedback remains a significant research challenge. We introduce a novel weight simulation technique that leverages electrotactile stimulation to induce slip illusions. These slip illusions occur when users grip an object with less force than a predefined threshold, allowing the device to modulate the grip force and encourage a tighter grip. In our approach, heavier virtual weights correspond to higher required grip forces. We conducted a series of user experiments to validate our technique, confirming that it effectively induces slip illusions. We also investigated the relationship between electrotactile sensations and grip force, and changes in force, demonstrating that this association enhances the weight perception experience. Lastly, we explored the mapping between grip force and perceived weight, observing strong linearity within participants but notable variability between individuals.2025HLHongnan Lin et al.Institute of Software, Chinese Academy of SciencesForce Feedback & Pseudo-Haptic WeightElectrical Muscle Stimulation (EMS)CHI
TutorCraftEase: Enhancing Pedagogical Question Creation with Large Language ModelsPedagogical questions are crucial for fostering student engagement and learning. In daily teaching, teachers pose hundreds of questions to assess understanding, enhance learning outcomes, and facilitate the transfer of theory-rich content. However, even experienced teachers often struggle to generate a large volume of effective pedagogical questions. To address this, we introduce TutorCraftEase, an interactive generation system that leverages large language models (LLMs) to assist teachers in creating pedagogical questions. TutorCraftEase enables the rapid generation of questions at varying difficulty levels with a single click, while also allowing for manual review and refinement. In a comparative user study with 39 participants, we evaluated TutorCraftEase against a traditional manual authoring tool and a basic LLM tool. The results show that TutorCraftEase can generate pedagogical questions comparable in quality to those created by experienced teachers, while significantly reducing their workload and time.2025WKWenhui Kang et al.University of Chinese Academy of Sciences; Institute of Software, Chinese Academy of Sciences, Beijing Key Laboratory of Human-Computer InteractionHuman-LLM CollaborationOnline Learning & MOOC PlatformsIntelligent Tutoring Systems & Learning AnalyticsCHI
TacTex: A Textile Interface with Seamlessly-Integrated Electrodes for High-Resolution electrotactile StimulationThis paper presents TacTex, a textile-based interface that provides high-resolution haptic feedback and touch-tracking capabilities. TacTex utilizes electrotactile stimulation, which has traditionally posed challenges due to limitations in textile electrode density and quantity. TacTex overcomes these challenges by employing a multi-layer woven structure that separates conductive weft and warp electrodes with non-conductive yarns. The driving system for TacTex includes a power supply, sensing board, and switch boards to enable spatial and temporal control of electrical stimuli on the textile, while simultaneously monitoring voltage changes. TacTex can stimulate a wide range of haptic effects, including static and dynamic patterns and different sensation qualities, with a resolution of $512 \times 512$ and \textcolor{black}{based on linear electrodes spaced as closely as 2mm}. We evaluate the performance of the interface with user studies and demonstrate the potential applications of TacTex interfaces in everyday textiles for adding haptic feedback.2024HLHongnan Lin et al.Institute of Software, Chinese Academy of SciencesVibrotactile Feedback & Skin StimulationShape-Changing Interfaces & Soft Robotic MaterialsElectronic Textiles (E-textiles)CHI
Exploring Locomotion Methods with Upright Redirected Views for VR Users in Reclining & Lying PositionsUsing VR in reclining & lying positions is getting common for users, but upward views caused by posture have to be redirected to be parallel to the ground as when users are standing. This affects users' locomotion performances in VR due to potential physical restrictions, and the visual-vestibular-proprioceptive conflict. This paper is among the first to investigate the suited locomotion methods and how reclining & lying positions and redirection affect them in such conditions. A user-elicitation study was carried out to construct a set of locomotion methods based on users' preferences when they were in different reclining & lying positions. A second study developed user-preferred 'tapping' and 'chair rotating' gestures, by evaluating their performances at various body reclining angles, we measured the general impacts of posture and redirection. The results showed that these methods worked effectively, but exposed some shortcomings, and users performed worst at 45-degree reclining angles. Finally, four upgraded methods were designed and verified to improve the locomotion performances.2023TLTianren Luo et al.Full-Body Interaction & Embodied InputImmersion & Presence ResearchIdentity & Avatars in XRUIST
Side-by-Side vs Face-to-Face: Evaluating Colocated Collaboration via a Transparent Wall-sized DisplayTraditional wall-sized displays mostly only support side-by-side co-located collaboration, while transparent displays naturally support face-to-face interaction. Many previous works assume transparent displays support collaboration. Yet it is unknown how exactly its afforded face-to-face interaction can support loose or close collaboration, especially compared to the side-by-side configuration offered by traditional large displays. In this paper, we used an established experimental task that operationalizes different collaboration coupling and layout locality, to compare pairs of participants collaborating side-by-side versus face-to-face in each collaborative situation. We compared quantitative measures and collected interview and observation data to further illustrate and explain our observed user behavior patterns. The results showed that the unique face-to-face collaboration brought by transparent display can result in more efficient task performance, different territorial behavior, and both positive and negative collaborative factors. Our findings provided empirical understanding about the collaborative experience supported by wall-sized transparent displays and shed light on its future design.2023JGJiangtao Gong et al.Collaboration ICSCW
Exploring Sensory Conflict Effect Due to Upright Redirection While Using VR in Reclining & Lying PositionsWhen users use Virtual Reality (VR) in nontraditional postures, such as while reclining or lying in relaxed positions, their views lean upwards and need to be corrected, to make sure they see upright contents and perceive the interactions as if they were standing. Such upright redirection is expected to cause visual-vestibular-proprioceptive conflict, affecting users' internal perceptions (e.g., body ownership, presence, simulator sickness) and external perceptions (e.g., egocentric space perception) in VR. Different body reclining angles may affect vestibular sensitivity and lead to the dynamic weighting of multi-sensory signals in the sensory integration. In the paper, we investigated the impact of upright redirection on users' perceptions, with users' physical bodies tilted at various angles backward and views upright redirected accordingly. The results showed that upright redirection led to simulator sickness, confused self-awareness, weak upright illusion, and increased space perception deviations to various extents when users are at different reclining positions, and the situations were the worst at the 45-degree conditions. Based on these results, we designed some illusion-based and sensory-based methods, that were shown effective in reducing the impact of sensory conflict through preliminary evaluations.2022TLTianren Luo et al.Motion Sickness & Passenger ExperienceFull-Body Interaction & Embodied InputImmersion & Presence ResearchUIST
ECGLens: Interactive Visual Exploration of Large Scale ECG Data for Arrhythmia DetectionThe Electrocardiogram (ECG) is commonly used to detect arrhythmias. Traditionally, a single ECG observation is used for diagnosis, making it difficult to detect irregular arrhythmias. Recent technology developments, however, have made it cost-effective to collect large amounts of raw ECG data over time. This promises to improve diagnosis accuracy, but the large data volume presents new challenges for cardiologists. This paper introduces ECGLens, an interactive system for arrhythmia detection and analysis using large-scale ECG data. Our system integrates an automatic heartbeat classification algorithm based on convolutional neural network, an outlier detection algorithm, and a set of rich interaction techniques. We also introduce A-glyph, a novel glyph designed to improve the readability and comparison of ECG signals. We report results from a comprehensive user study showing that A-glyph improves the efficiency in arrhythmia detection, and demonstrate the effectiveness of ECGLens in arrhythmia detection through two expert interviews.2018KXKe Xu et al.The Hong Kong University of Science and TechnologyInteractive Data VisualizationMedical & Scientific Data VisualizationCHI