Conversational agents that participate in or mediate group interaction introduce challenges that extend beyond supporting individual users, raising new questions about how agents participate in and influence groups. To characterise this emerging design space, we present a systematic review of 53 peer-reviewed studies on group conversational agents (GCAs). We analyse how GCAs intervene in group-level processes, including participation regulation, conflict mediation, task alignment, and execution support. Using concepts from group research as an analytic lens, we organise prior GCA work around recurring group interactional challenges (orientation, conflict, alignment, and execution), and examine the roles agents are designed to play in addressing these challenges. We find that GCAs are predominantly designed as short-term, role-bounded interventions targeting isolated challenges in bounded interactional contexts. We further identify recurring structural tensions in GCA design, including tradeoffs between visibility and discretion, proactivity and group autonomy, and agent authority and group ownership. Together, these findings clarify how current GCAs are positioned within group interaction, surface the implicit assumptions embedded in their designs, and outline open questions for future research on conversational agents as group-level interventions.

Intergenerational conversations often break down when differences in tone, language, or expectations lead participants to feel dismissed or misunderstood. In this work, we explore how people envision AI-driven chatbot interventions for addressing communication problems in text-based intergenerational family chat. We conducted a scenario-based design interview with 10 pairs of family members from different generations, in which participants designed chatbot interventions that varied in intervention target and timing. Our findings show that participants expect chatbots to perform multiple themes of intervention, including mediating understanding, providing emotional support, offering evaluative commentary, and guiding interaction through behavioral suggestions. These expectations varied systematically across intervention contexts, giving rise to distinct chatbot roles such as neutral mediators, message coaches, repair facilitators, and emotion regulators. Across these roles, participants positioned chatbots as moral advisors that evaluate communicative appropriateness and exercise varying degrees of moral authority. Rather than prescribing specific system behaviors, this work offers a conceptual and exploratory account of AI-mediated intervention in intergenerational communication, and articulates key design tensions that arise when chatbots are imagined as socially and morally involved actors in intimate family interactions.

Designing adaptive tutoring systems for software learning presents challenges in determining appropriate instructional modalities. To inform the design of such systems, we conducted an observational study of ten human teacher-student pairs (N=10), where experienced design software users taught novices two new graphic design software features through multi-step procedures. These lessons were limited to three communication channels (speech, visual annotations, and remote screen control) to mimic possible AI tutor modalities. We found that annotations complement speech with spatial precision and remote control complements it with spatial and temporal precision, but both cause intrusion to learner agency. Teachers adaptively select modalities to balance the need for instruction progress with students’ cognitive engagement and sense of digital territory ownership. Our results provide further support to the contiguity principles and the value of agency in learning, while suggesting precision-agency trade-off and digital territoriality as new design constraints for adaptive software guidance.

Low-end earphones are widely spread due to their affordability, but their limited speaker hardware often leads to poor music playback quality. This raises a key question: Can we compensate for hardware limitations to enhance the listening experience without modifying the device? Existing EQ-based approaches attempt this, but they rely on frequency response curves (FRCs) measured under ideal conditions, which fail to capture real-world distortions such as harmonic and intermodulation effects.

In the digital age, readers value quantitative journalism that is clear, concise, analytical, and humancentred. To understand complex topics, they often piece together scattered facts from multiple articles. Visual storytelling can transform fragmented information into clear, engaging narratives, yet its use with unstructured online articles remains largely unexplored. To fill this gap, we present Compendia, an automated system that analyzes online articles in response to a user's query and generates a coherent data story tailored to the user's informational needs. Compendia addresses key challenges of storytelling from unstructured text through two modules covering: Online Article Retrieval, which gathers relevant articles; Data Fact Extraction, which identifies, validates, and refines quantitative facts; Fact Organization, which clusters and merges related facts into coherent thematic groups; and Visual Storytelling, which transforms the organized facts into narratives with visualizations in an interactive scrollytelling interface. We evaluated Compendia through a quantitative analysis, confirming the accuracy in fact extraction and organization, and through two user studies with 16 participants, demonstrating its usability, effectiveness, and ability to produce engaging visual stories for open-ended queries.

Quantum Neural Networks (QNNs) represent a promising fusion of quantum computing and neural network architectures, offering speed-ups and efficient processing of high-dimensional, entangled data. A crucial component of QNNs is the encoder, which maps classical input data into quantum states. However, choosing suitable encoders remains a significant challenge, largely due to the lack of systematic guidance and the trial-and-error nature of current approaches. This process is further impeded by two key challenges: (1) the difficulty in evaluating encoded quantum states prior to training, and (2) the lack of intuitive methods for analyzing an encoder's ability to effectively distinguish data features. To address these issues, we introduce a novel visualization tool, XQAI-Eyes, which enables QNN developers to compare classical data features with their corresponding encoded quantum states and to examine the mixed quantum states across different classes. By bridging classical and quantum perspectives, XQAI-Eyes facilitates a deeper understanding of how encoders influence QNN performance. Evaluations across diverse datasets and encoder designs demonstrate XQAI-Eyes's potential to support the exploration of the relationship between encoder design and QNN effectiveness, offering a holistic and transparent approach to optimizing quantum encoders. Moreover, domain experts used XQAI-Eyes to derive two key practices for quantum encoder selection, grounded in the principles of pattern preservation and feature mapping.

Design studies aim to develop visualization solutions for real-world problems across various application domains. Recently, the emergence of large language models (LLMs) has introduced new opportunities to enhance the design study process, providing capabilities such as creative problem-solving, data handling, and insightful analysis. However, despite their growing popularity, there remains a lack of systematic understanding of how LLMs can effectively assist researchers in visualization-specific design studies. In this paper, we conducted a rnulti-stage qualitative study to fill this gap, which involved 30 design study researchers from diverse backgrounds and expertise levels. Through in-depth interviews and carefully-designed questionnaires, we investigated strategies for utilizing LLMs, the challenges encountered, and the practices used to overcome them. We further compiled the roles that LLMs can play across different stages of the design study process. Our findings highlight practical implications to inform visualization practitioners, and also provide a framework for leveraging LLMs to facilitate the design study process in visualization research.

Foundation models are rapidly improving the capability of robots in performing everyday tasks autonomously such as meal preparation, yet robots will still need to be instructed by humans due to model performance, the difficulty of capturing user preferences, and the need for user agency. Robots can be instructed using various methods-natural language conveys immediate instructions but can be abstract or ambiguous, whereas end-user programming supports longer-horizon tasks but interfaces face difficulties in capturing user intent. In this work, we propose using direct manipulation of images as an alternative paradigm to instruct robots, and introduce a specific instantiation called ImageInThat which allows users to perform direct manipulation on images in a timeline-style interface to generate robot instructions. Through a user study, we demonstrate the efficacy of ImageInThat to instruct robots in kitchen manipulation tasks, comparing it to a text-based natural language instruction method. The results show that participants were faster with ImageInThat and preferred to use it over the text-based method. Supplementary material including code can be found at: https://image-in-that.github.io/.

Modern decision-making scenarios often involve data that is both high-dimensional and rich in higher-order contextual information, where existing bandits algorithms fail to generate effective policies. In response, we propose in this paper a generalized linear tensor bandits algorithm designed to tackle these challenges by incorporating low-dimensional tensor structures, and further derive a unified analytical framework of the proposed algorithm. Specifically, our framework introduces a convex optimization approach with the weakly decomposable regularizers, enabling it to not only achieve better results based on the tensor low-rankness structure assumption but also extend to cases involving other low-dimensional structures such as slice sparsity and low-rankness. The theoretical analysis shows that, compared to existing low-rankness tensor result, our framework not only provides better bounds but also has a broader applicability. Notably, in the special case of degenerating to low-rank matrices, our bounds still offer advantages in certain scenarios.

Prewriting is the process of generating and organising ideas before a first draft. It consists of a combination of informal, iterative, and semi-structured strategies such as visual diagramming, which poses a challenge for collaborating with large language models (LLMs) in a turn-taking conversational manner. We present Polymind, a visual diagramming tool that leverages multiple LLM-powered agents to support prewriting. The system features a parallel collaboration workflow in place of the turn-taking conversational interactions. It defines multiple ''microtasks'' to simulate group collaboration scenarios such as collaborative writing and group brainstorming. Instead of repetitively prompting a chatbot for various purposes, Polymind enables users to orchestrate multiple microtasks simultaneously. Users can configure and delegate customised microtasks, and manage their microtasks by specifying task requirements and toggling visibility and initiative. Our evaluation revealed that, compared to ChatGPT, users had more customizability over collaboration with Polymind, and were thus able to quickly expand personalised writing ideas during prewriting.

Many pre-operative overall survival (OS) prediction methods have been proposed to assist personalized treatment of diffuse glioma for better prognosis. Most of them utilize pre-operative data, while post-operative data, which contains essential prognosis-related information (e.g., surgical outcomes and lesion evolution) is neglected, hindering prediction accuracy. However, incorporating post-operative data could make OS prediction inapplicable at pre-operative stage, affecting clinical utility. To address this contradiction, in this paper, we propose an effective framework that leverages longitudinal data (pre- and post-operative data) to enhance pre-operative OS prediction. Specifically, two OS prediction networks are built in a knowledge distillation framework. One is the teacher network trained with longitudinal data, and the other is the student network relying solely on pre-operative data. Distillation of deep features is conducted to align the performance of the student network with that of the teacher network. Moreover, mass effect and its distillation are adopted to incorporate lesion evolution information, further enhancing prediction performance. Based on our framework, the student network can leverage essential post-operative information without compromising its applicability at pre-operative stage. Experiments on both in-house and public datasets demonstrate that the student network outperforms all state-of-the-art methods under evaluation with statistical significance. Further ablation study reveals that distillation of mass effect and deep features play positive roles in OS prediction. Moreover, new prognosis-related factors are discovered by comparing the student network with and without distillation.

Generative AI tools can provide people with the ability to create virtual environments and scenes with natural language prompts. Yet, how people will formulate such prompts is unclear—particularly when they inhabit the environment that they are designing. For instance, it is likely that a person might say, “Put a chair here,” while pointing at a location. If such linguistic and embodied features are common to people’s prompts, we need to tune models to accommodate them. In this work, we present a Wizard of Oz elicitation study with 22 participants, where we studied people’s implicit expectations when verbally prompting such programming agents to create interactive VR scenes. Our findings show when people prompted the agent, they had several implicit expectations of these agents: (1) they should have an embodied knowledge of the environment; (2) they should understand embodied prompts by users; (3) they should recall previous states of the scene and the conversation, and that (4) they should have a commonsense understanding of objects in the scene. Further, we found that participants prompted differently when they were prompting in situ (i.e. within the VR environment) versus ex situ (i.e. viewing the VR environment from the outside). To explore how these lessons could be applied, we designed and built Ostaad, a conversational programming agent that allows non-programmers to design interactive VR experiences that they inhabit. Based on these explorations, we outline new opportunities and challenges for conversational programming agents that create VR environments.

Mixed Reality enables hybrid workspaces where physical and virtual monitors are adaptively created and moved to suit the current environment and needs. However, in shared settings, individual users’ workspaces are rarely aligned and can vary significantly in the number of monitors, available physical space, and workspace layout, creating inconsistencies between workspaces which may cause confusion and reduce collaboration. We present Desk2Desk, an optimization-based approach for remote collaboration in which the hybrid workspaces of two collaborators are fully integrated to enable immersive side-by-side collaboration. The optimization adjusts each user’s workspace in layout and number of shared monitors and creates a mapping between workspaces to handle inconsistencies between workspaces due to physical constraints (e.g. physical monitors). We show in a user study how our system adaptively merges dissimilar physical workspaces to enable immersive side-by-side collaboration, and demonstrate how an optimization-based approach can effectively address dissimilar physical layouts.

Live and pre-recorded video tutorials are an effective means for teaching physical skills such as cooking or prototyping electronics. A dedicated cameraperson following an instructor’s activities can improve production quality. However, instructors who do not have access to a cameraperson’s help often have to work within the constraints of static cameras. We present Stargazer, a novel approach for assisting with tutorial content creation with a camera robot that autonomously tracks regions of interest based on instructor actions to capture dynamic shots. Instructors can adjust the camera behaviors of Stargazer with subtle cues, including gestures and speech, allowing them to fluidly integrate camera control commands into instructional activities. Our user study with six instructors, each teaching a distinct skill, showed that participants could create dynamic tutorial videos with a diverse range of subjects, camera framing, and camera angle combinations using Stargazer.

Virtual Reality (VR) can completely immerse users in a virtual world and provide little awareness of bystanders in the surrounding physical environment. Current technologies use predefined guardian area visualizations to set safety boundaries for VR interactions. However, bystanders cannot perceive these boundaries and may collide with VR users if they accidentally enter guardian areas. In this paper, we investigate four awareness techniques on mobile phones and smartwatches to help bystanders avoid invading guardian areas. These techniques include augmented reality boundary overlays and visual, auditory, and haptic alerts indicating bystanders' distance from guardians. Our findings suggest that the proposed techniques effectively keep participants clear of the safety boundaries. More specifically, using augmented reality overlays, participants could avoid guardians with less time, and haptic alerts caused less distraction.

How-to videos are often shot using camera angles that may not be optimal for learning motor tasks, with a prevalent use of third-person perspective. We present immersivePOV, an approach to film how-to videos from an immersive first-person perspective using a head-mounted 360° action camera. immersivePOV how-to videos can be viewed in a Virtual Reality headset, giving the viewer an eye-level viewpoint with three Degrees of Freedom. We evaluated our approach with two everyday motor tasks against a baseline first-person perspective and a third-person perspective. In a between-subjects study, participants were assigned to watch the task videos and then replicate the tasks. Results suggest that immersivePOV reduced perceived cognitive load and facilitated task learning. We discuss how immersivePOV can also streamline the video production process for content creators. Altogether, we conclude that immersivePOV is an effective approach to film how-to videos for learners and content creators alike.

Online synchronous tutoring allows for immediate engagement between instructors and audiences over distance. However, tutoring physical skills remains challenging because current telepresence approaches may not allow for adequate spatial awareness, viewpoint control of the demonstration activities scattered across an entire work area, and the instructor’s sufficient awareness of the audience. We present Asteroids, a novel approach for tangible robotic telepresence, to enable workbench-scale physical embodiments of remote people and tangible interactions by the instructor. With Asteroids, the audience can actively control a swarm of mini-telepresence robots, change camera positions, and switch to other robots’ viewpoints. Demonstrators can perceive the audiences’ physical presence while using tangible manipulations to control the audience’s viewpoints and presentation flow. We conducted an exploratory evaluation for Asteroids with 12 remote participants in a model-making tutorial scenario with an architectural expert demonstrator. Results suggest our unique features benefitted participants’ engagement, sense of presence, and understanding.

Collaborative exploration of 360 videos with contemporary interfaces is challenging because collaborators do not have awareness of one another's viewing activities. Tourgether360 enhances social exploration of 360° tour videos using a pseudo-spatial navigation technique that provides both an overhead "context" view of the environment as a minimap, as well as a shared pseudo-3D environment for exploring the video. Collaborators are embodied as avatars along a track depending on their position in the video timeline and can point and synchronize their playback. We evaluated the Tourgether360 concept through two studies: first, a comparative study with a simplified version of Tourgether360 with collaborator embodiments and a minimap versus a conventional interface; second, an exploratory study where we studied how collaborators used Tourgether360 to navigate and explore 360° environments together. We found that participants adopted the Tourgether360 approach with ease and enjoyed the shared social aspects of the experience. Participants reported finding the experience similar to an interactive social video game.

Live streaming has become increasingly popular, with most streamers presenting their real-life appearance. However, Virtual YouTubers (VTubers), virtual 2D or 3D avatars that are voiced by humans, are emerging as live streamers and attracting a growing viewership in East Asia. Although prior research has found that many viewers seek real-life interpersonal interactions with real-person streamers, it is currently unknown what makes VTuber live streams engaging or how they are perceived differently than real-person streamers. We conducted an interview study to understand how viewers engage with VTubers and perceive the identities of the voice actors behind the avatars (i.e., Nakanohito). The data revealed that Virtual avatars bring unique performative opportunities which result in different viewer expectations and interpretations of VTuber behavior. Viewers intentionally upheld the disembodiment of VTuber avatars from their voice actors. We uncover the nuances in viewer perceptions and attitudes and further discuss the implications of VTuber practices to the understanding of live streaming in general.

Remotely controlled camera drones can support live, dynamic, and interactive virtual tours for travelers to overcome distance, expense, and health barriers. Yet, assigning one drone to one traveler may incur unnecessary waste of resources, and an abundance of concurrent drones raises safety concerns. While sharing the input and output of a single drone among multiple concurrent users can alleviate these limitations, standard control sharing protocols, such as turn-taking, are often inefficient. We present Constellation, a multi-user drone control system that synthesizes diverse user goals and generates efficient flight paths for the group. It supports point-of-interest specification on both static 3D environmental maps and live camera views. The generated paths minimize all users’ total extra waiting time. A web-based study with 16 participants show that Constellation could help groups navigate to their points-of-interest faster in comparison to the turn-taking baseline.

In this paper, we present HoloBoard, an interactive large-format pseduo-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 are potentially valuable for lecturing in class. We conducted a controlled experimental study to compare a HoloBoard class with a normal class through 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.

An increasingly popular way of experiencing remote places is by viewing 360° virtual tour videos, which show the surrounding view while traveling through an environment. However, finding particular locations in these videos can be difficult because current interfaces rely on distorted frame previews for navigation. To alleviate this usability issue, we propose Route Tapestries, continuous orthographic-perspective projection of scenes along camera routes. We first introduce an algorithm for automatically constructing Route Tapestries from a 360° video, inspired by the slit-scan photography technique. We then present a desktop video player interface using a Route Tapestry timeline for navigation. An online evaluation using a target-seeking task showed that Route Tapestries allowed users to locate targets 22% faster than with YouTube-style equirectangular previews and reduced the failure rate by 75% compared to a more conventional row-of-thumbnail strip preview. Our results highlight the value of reducing visual distortion and providing continuous visual contexts in previews for navigating 360°virtual tour videos.

Camera drones, a rapidly emerging technology, offer people the ability to remotely inspect an environment with a high degree of mobility and agility. However, manual remote piloting of a drone is prone to errors. In contrast, autopilot systems can require a significant degree of environmental knowledge and are not necessarily designed to support flexible visual inspections. Inspired by camera manipulation techniques in interactive graphics, we designed StarHopper, a novel touch screen interface for efficient object-centric camera drone navigation, in which a user directly specifies the navigation of a drone camera relative to a specified object of interest. The system relies on minimal environmental information and combines both manual and automated control mechanisms to give users the freedom to remotely explore an environment with efficiency and accuracy. A lab study shows that StarHopper offers an efficiency gain of 35.4% over manual piloting, complimented by an overall user preference towards our object-centric navigation system.

Intensive exploration and navigation of hierarchical lists on smartphones can be tedious and time-consuming as it often requires users to frequently switch between multiple views. To overcome this limitation, we present PinchList, a novel interaction design that leverages pinch gestures to support seamless exploration of multi-level list items in hierarchical views. With PinchList, sub-lists are accessed with a pinch-out gesture whereas a pinch-in gesture navigates back to the previous level. Additionally, pinch and flick gestures are used to navigate lists consisting of more than two levels. We conduct a user study to refine the design parameters of PinchList such as a suitable item size, and quantitatively evaluate the target acquisition performance using pinch-in/out gestures in both scrolling and non-scrolling conditions. In a second study, we compare the performance of PinchList in a hierarchal navigation task with two commonly used touch interfaces for list browsing: pagination and expand-and-collapse interfaces. The results reveal that PinchList is significantly faster than other two interfaces in accessing items located in hierarchical list views. Finally, we demonstrate that PinchList enables a host of novel applications in list-based interaction?

Selecting an item of interest on smartwatches can be tedious and time-consuming as it involves a series of swipe and tap actions. We present PageFlip, a novel method that combines into a single action multiple touch operations such as command invocation and value selection for efficient interaction on smartwatches. PageFlip operates with a page flip gesture that starts by dragging the UI from a corner of the device. We first design PageFlip by examining its key design factors such as corners, drag directions and drag distances. We next compare PageFlip to a functionally equivalent radial menu and a standard swipe and tap method. Results reveal that PageFlip improves efficiency for both discrete and continuous selection tasks. Finally, we demonstrate novel smartwatch interaction opportunities and a set of applications that can benefit from PageFlip.

Transparent displays can serve as an important collaborative medium supporting face-to-face interactions over a shared visual work surface. Such displays enhance workspace awareness: when a person is working on one side of a transparent display, the person on the other side can see the other's body, hand gestures, gaze and what he or she is actually manipulating on the shared screen. Even so, we argue that designing such transparent displays must go beyond current offerings if it is to support collaboration. First, both sides of the display must accept interactive input, preferably by at least touch and / or pen, as that affords the ability for either person to directly interact with the workspace items. Second, and more controversially, both sides of the display must be able to present different content, albeit selectively. Third (and related to the second point), because screen contents and lighting can partially obscure what can be seen through the surface, the display should visually enhance the actions of the person on the other side to better support workspace awareness. We describe our prototype FACINGBOARD-2 system, where we concentrate on how its design supports these three collaborative requirements.