People speak aloud to externalize thoughts as one way to help clarify and organize them. Although Speech-to-text can capture these thoughts, transcripts can be difficult to read and make sense due to disfluencies, repetitions and potential disorganization. To support thinking through verbalization, we introduce Orality, which extracts key information from spoken content, performs semantic analysis through LLMs to form a node-link diagram in an interactive canvas. Instead of reading and working with transcripts, users could manipulate clusters of nodes and give verbal instructions to re-extract and organize the content in other ways. It also provides AI-generated inspirational questions and detection of logical conflicts. We conducted a lab study with twelve participants comparing Orality against speech interaction with ChatGPT. We found that Orality can better support users in clarifying and developing their thoughts. The findings also identified the affordances of both graphical and conversational thought clarification tools and derived design implications.

Transcripts displayed on dictation interfaces can be hard to read due to recognition errors and disfluencies. LLM-based text auto-correction could help, but changing the text during production could lead to distraction and unintended phrasing. To understand how to balance readability, attention, and accuracy, we conducted an eye-tracking experiment with 20 participants to compare five dictation interfaces: PLAIN (real-time transcription), AOC (periodic corrections), RAKE (keyword highlights), GP-TSM (grammar-preserving highlights), and SUMMARY (LLM-generated abstractive summary). By analyzing participants’ gaze patterns during speech composition and reviewing processes, we found that during composition, participants spent only 7%-11% of their time in active reading regardless of the interface. Although SUMMARY introduced unfamiliar words and phrasing during composition, it was easier to read and more preferred by participants. Our findings suggest a high user tolerance for altering spoken words in LLM-enabled diction interfaces.

Storyboarding is an established method for designing user experiences. Generative AI can support this process by helping designers quickly create visual narratives. However, existing tools mainly focus on improving the accuracy of text-to-image generation. There is a lack of understanding on how to effectively support the entire creative process of storyboarding and how to develop AI-powered tools to be integrated into designers' diverse workflows. In this work, we designed and developed StoryDiffusion, a system that integrates text-to-text and text-to-image models, to support the generation of narratives and images in a single pipeline. In a user study, we observed 12 UX design students using the system for both concept ideation and illustration tasks. Our findings identified AI-directed vs. user-directed creative strategies in both tasks and revealed the importance of supporting the interchange between narrative iteration and image generation. We also found effects of the design tasks on their strategies and preferences, providing insights for future development. © 2025 Copyright held by the owner/author(s).

Mixed reality platforms allow users to create virtual environments, yet novice users struggle with both ideation and execution in spatial design. While existing AI models can automatically generate scenes based on user prompts, the lack of interactive control limits users' ability to iteratively steer the output. In this paper, we present EchoLadder, a novel human-AI collaboration pipeline that leverages large vision-language model (LVLM) to support interactive scene modification in virtual reality. EchoLadder accepts users' verbal instructions at varied levels of abstraction and spatial specificity, generates concrete design suggestions throughout a progressive design process. The suggestions can be automatically applied, regenerated and retracted by users' toggle control.Our ablation study showed effectiveness of our pipeline components. Our user study found that, compared to baseline without showing suggestions, EchoLadder better supports user creativity in spatial design. It also contributes insights on users' progressive design strategies under AI assistance, providing design implications for future systems.

Optical See-through Head-Mounted Displays (OHMDs) offer new opportunities for completing complex information processing tasks on the go. We introduce GlassMail, a Large Language Models (LLMs)-based wearable assistant on OHMDs for mobile email creation. Our formative study identified two challenges of the LLM-based wearable email assistant: (i) achieving efficient and accurate understanding of user intentions, and (ii) ensuring effective information presentation for email processes. Through two empirical studies, we developed a "Single Turn with Optional Clarification " approach for accurate user intention recognition and a "Fade Context with Optional Audio " mode for effective email processing. An observation study then evaluated GlassMail ’s feasibility in composing formal and semi-formal emails, supporting the usefulness and effectiveness of GlassMail in simple scenarios and yielding insights into potential future improvements for complex scenarios. We further discuss the design implications for the future development of wearable AI-enabled assistants.

While effective for recording and sharing experiences, traditional in-context writing tools are relatively passive and unintelligent, serving more like instruments rather than companions. This reduces primary task (e.g., travel) enjoyment and hinders high-quality writing. Through formative study and iterative development, we introduce PANDALens, a Proactive AI Narrative Documentation Assistant built on an Optical See-Through Head Mounted Display that supports personalized documentation in everyday activities. PANDALens observes multimodal contextual information from user behaviors and environment to confirm interests and elicit contemplation, and employs Large Language Models to transform such multimodal information into coherent narratives with significantly reduced user effort. A real-world travel scenario comparing PANDALens with a smartphone alternative confirmed its effectiveness in improving writing quality and travel enjoyment while minimizing user effort. Accordingly, we propose design guidelines for AI-assisted in-context writing, highlighting the potential of transforming them from tools to intelligent companions.

Dictation enables efficient text input on mobile devices. However, writing with speech can produce disfluent, wordy, and incoherent text and thus requires heavy post-processing. This paper presents Rambler, an LLM-powered graphical user interface that supports gist-level manipulation of dictated text with two main sets of functions: gist extraction and macro revision. Gist extraction generates keywords and summaries as anchors to support the review and interaction with spoken text. LLM-assisted macro revisions allow users to respeak, split, merge, and transform dictated text without specifying precise editing locations. Together they pave the way for interactive dictation and revision that help close gaps between spontaneously spoken words and well-structured writing. In a comparative study with 12 participants performing verbal composition tasks, Rambler outperformed the baseline of a speech-to-text editor + ChatGPT, as it better facilitates iterative revisions with enhanced user control over the content while supporting surprisingly diverse user strategies.

Sketching in Virtual Reality (VR) is challenging mainly due to the absence of physical surface support and virtual depth perception cues, which induce high cognitive and sensorimotor load. This paper presents WieldingCanvas, an interactive VR sketching platform that integrates canvas manipulations to draw lines and curves in 3D. Informed by real-life examples of two-handed creative activities, WieldingCanvas interprets users’ spatial gestures to move, swing, rotate, transform, or fold a virtual canvas, whereby users simply draw primitive strokes on the canvas, which are turned into finer and more sophisticated shapes via the manipulation of the canvas. We evaluated the capability and user experience of WieldingCanvas with two studies where participants were asked to sketch target shapes. A set of freehand sketches of high aesthetic qualities were created, and the results demonstrated that WieldingCanvas can assist users with creating 3D sketches.

Collaboration can amalgamate diverse ideas, styles, and visual elements, fostering creativity and innovation among different designers. In collaborative design, sketches play a pivotal role as a means of expressing design creativity. However, designers often tend to not openly share these meticulously crafted sketches. This phenomenon of data island in the design area hinders its digital transformation under the third wave of AI. In this paper, we introduce a Federated Generative Artificial Intelligence Clothing system, namely StyleWe, employing federated learning to aid in sketch design. StyleWe is committed to establishing an ecosystem wherein designers can exchange sketch styles among themselves. Through StyleWe, designers can generate sketches that incorporate various designers' styles from their peers, drawing inspiration from collaboration without the need for data disclosure or upload. Extensive performance evaluations and user studies indicate that our StyleWe system can produce multi-styled sketches of comparable quality to human-designed ones while significantly enhancing efficiency compared to hand-drawn sketches.

Traditional 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.

Wizard of Oz (WoZ) as a prototyping method has been used to simulate intelligent user interfaces, particularly for speech-based systems. However, as our societies' expectations on artificial intelligence (AI) grows, the question remains whether a single Wizard is sufficient for it to simulate smarter systems and more complex interactions. Optimistic visions of 'what artificial intelligence (AI) can do' places demands on WoZ platforms to simulate smarter systems and more complex interactions. This raises the question of whether the typical approach of employing a single Wizard is sufficient. Moreover, while existing work has employed multiple Wizards in WoZ studies, a multi-Wizard approach has not been systematically studied in terms of feasibility, effectiveness, and challenges. We offer Wizundry, a real-time, web-based WoZ platform that allows multiple Wizards to collaboratively operate a speech-to-text based system remotely. We outline the design and technical specifications of our open-source platform, which we iterated over two design phases. We report on two studies in which participant-Wizards were tasked with negotiating how to cooperatively simulate an interface that can handle natural speech for dictation and text editing as well as other intelligent text processing tasks. We offer qualitative findings on the Multi-Wizard experience for Dyads and Triads of Wizards. Our findings reveal the promises and challenges of the multi-Wizard approach and open up new research questions.

Existing text selection techniques on touchscreen focus on improving the control for moving the carets. Coarse-grained text selection on word and phrase levels has not received much support beyond word-snapping and entity recognition. We introduce 1D-Touch, a novel text selection method that complements the carets-based sub-word selection by facilitating the selection of semantic units of words and above. This method employs a simple vertical slide gesture to expand and contract a selection area from a word. The expansion can be by words or by semantic chunks ranging from sub-phrases to sentences. This technique shifts the concept of text selection, from defining a range by locating the first and last words, towards a dynamic process of expanding and contracting a textual semantic entity. To understand the effects of our approach, we prototyped and tested two variants: WordTouch, which offers a straightforward word-by-word expansion, and ChunkTouch, which leverages NLP to chunk text into syntactic units, allowing the selection to grow by semantically meaningful units in response to the sliding gesture. Our evaluation, focused on the coarse-grained selection tasks handled by 1D-Touch, shows a 20% improvement over the default word-snapping selection method on Android.

3D modelling and printing are becoming increasingly popular. However, beginners often face high barriers of entry when trying to use existing 3D modelling tools, even for creating simple objects. This is further complicated on mobile devices by the lack of direct manipulation in the Z dimension. In this paper, we explore the possibility of using foldable mobile devices for modelling simple objects by constructing a 2.5D display and interaction space with folded touch screens. We present a set of novel interaction techniques - AngleCAD, which allows users to view and navigate a 3D space through folded screens, and to modify the 3D object using the physical support of touchscreens and folding angles. The design of these techniques was inspired by woodworking practices to support surface-based operations that allow users to cut, snap and taper objects directly with the touch screen, and extrude and drill them according to the physical fold angle. A preliminary study identified the benefits of this approach and the key design factors that affect the user experience.

Voice dictation is increasingly used for text entry, especially in mobile scenarios. However, the speech-based experience gets disrupted when users must go back to a screen and keyboard to review and edit the text. While existing dictation systems focus on improving transcription and error correction, little is known about how to support speech input for the entire text creation process, including composition, reviewing and editing. We conducted an experiment in which ten pairs of participants took on the roles of authors and typists to work on a text authoring task. By analysing the natural language patterns of both authors and typists, we identified new challenges and opportunities for the design of future dictation interfaces, including the ambiguity of human dictation, the differences between audio-only and with screen, and various passive and active assistance that can potentially be provided by future systems.

Interacting with out of reach or occluded VR objects can be cumbersome. Although users can change their position and orientation, such as via teleporting, to help observe and select, doing so frequently may cause loss of spatial orientation or motion sickness. We present vMirror, an interactive widget leveraging reflection of mirrors to observe and select distant or occluded objects. We first designed interaction techniques for placing mirrors and interacting with objects through mirrors. We then conducted a formative study to explore a semi-automated mirror placement method with manual adjustments. Next, we conducted a target-selection experiment to measure the effect of the mirror’s orientation on users’ performance. Results showed that vMirror can be as efficient as direct target selection for most mirror orientations. We further compared vMirror with teleport technique in a virtual treasure hunt game and measured participants’ task performance and subjective experiences. Finally, we discuss vMirorr user experience and present future directions.

On-the-go text-editing is difficult, yet frequently done in everyday lives. Using smartphones for editing text forces users into a heads-down posture which can be undesirable and unsafe. We present EYEditor, a heads-up smartglass-based solution that displays the text on a see-through peripheral display and allows text-editing with voice and manual input. The choices of output modality (visual and/or audio) and content presentation were made after a controlled experiment, which showed that sentence-by-sentence visual-only presentation is best for optimizing users' editing and path-navigation capabilities. A second experiment formally evaluated EYEditor against the standard smartphone-based solution for tasks with varied editing complexities and navigation difficulties. The results showed that EYEditor outperformed smartphones as either the path OR the task became more difficult. Yet, the advantage of EYEditor became less salient when both the editing and navigation was difficult. We discuss trade-offs and insights gained for future heads-up text-editing solutions.

We transform traditional experience writing into in-situ voice-based multimedia authoring. Documenting experiences digitally in blogs and journals is a common activity that allows people to socially connect with others by sharing their experiences (e.g. travelogue). However, documenting such experiences can be time-consuming and cognitively demanding as it is typically done OUT-OF-CONTEXT (after the actual experience). We propose in-situ voice-based multimedia authoring (IVA), an alternative workflow to allow IN-CONTEXT experience documentation. Unlike the traditional approach, IVA encourages in-context content creations using voice-based multimedia input and stores them in multi-modal “snippets”. The snippets can be rearranged to form multimedia articles and can be published with light copy-editing. To improve the output quality from impromptu speech, Q&A scaffolding was introduced to guide the content creation. We implement the IVA workflow in an android application, LiveSnippets - and qualitatively evaluate it under three scenarios (travel writing, recipe creation, product review). Results demonstrated that IVA can effectively lower the barrier of writing with acceptable trade-offs in multitasking.

Existing voice-based interfaces have limited support for text editing, especially when seeing the text is difficult, e.g., while walking or cooking. This research develops voice interaction techniques for eyes-free text editing. First, with a Wizard-of-Oz study, we identified two primary user strategies: using commands, e.g., “ replace go with goes ” and re-dictating over an erroneous portion, e.g., correcting “he go there” by saying “he goes there.” To support these user strategies with an actual system implementation, we developed two eyes-free voice interaction techniques, Commanding and Re-dictation , and evaluated them with a controlled experiment. Results showed that while Re-dictation performs significantly better for more semantically complex edits, Commanding is more suitable for making one-word edits, especially deletions. We developed VoiceRev to combine both the techniques in the same interface and evaluated it with realistic tasks. Results showed improved usability of the combined techniques over either of the two techniques used individually.

Existing platforms for sharing locative digital content rely on the use of mobile phones for accessing the content. This can be a major deterrent to wider public access and also hinders immediacy and 'in the moment' discoverability. Building on previous work in situated public installations, we developed Pinsight, a novel platform for enabling end-users, such as local communities, to create and share digital content in-situ with public audiences through physical interactive devices. Pinsight is based on a set of design principles that focus on supporting both the expressiveness of content creators and the appeal to public audiences. This paper describes the design of the platform and how it supports sharing knowledge in ways different to conventional media. Through preliminary evaluations and two in-the-wild studies, we explore how such a situated technology can be used by different user groups (content designers, history communities, local residents) for sharing content with public audiences (visitors, pedestrians, residents) in different contexts.

We contribute SurfaceConstellations, a modular hardware platform for linking multiple mobile devices to easily create novel cross-device workspace environments. Our platform combines the advantages of multi-monitor workspaces and multi-surface environments with the flexibility and extensibility of more recent cross-device setups. The SurfaceConstellations platform includes a comprehensive library of 3D-printed link modules to connect and arrange tablets into new workspaces, several strategies for designing setups, and a visual configuration tool for automatically generating link modules. We contribute a detailed design space of cross-device workspaces, a technique for capacitive links between tablets for automatic recognition of connected devices, designs of flexible joint connections, detailed explanations of the physical design of 3D printed brackets and support structures, and the design of a web-based tool for creating new SurfaceConstellation setups.

Multi-touch wall-sized displays afford collaborative exploration of large datasets and re-organization of digital content. However, standard touch interactions, such as dragging to move content, do not scale well to large surfaces and were not designed to support collaboration, such as passing an object around. This paper introduces CoReach, a set of collaborative gestures that combine input from multiple users in order to manipulate content, facilitate data exchange and support communication. We conducted an observational study to inform the design of CoReach, and a controlled study showing that it reduced physical fatigue and facilitated collaboration when compared with traditional multi-touch gestures. A final study assessed the value of also allowing input through a handheld tablet to manipulate content from a distance.

Wall-sized displays support small groups of users working together on large amounts of data. Observational studies of such settings have shown that users adopt a range of collaboration styles, from loosely to closely coupled. Shared interaction techniques, in which multiple users perform a command collaboratively, have also been introduced to support co-located collaborative work. In this paper, we operationalize five collaborative situations with increasing levels of coupling, and test the effects of providing shared interaction support for a data manipulation task in each situation. The results show the benefits of shared interaction for close collaboration: it encourages collaborative manipulation, it is more efficient and preferred by users, and it reduces physical navigation and fatigue. We also identify the time costs caused by disruption and communication in loose collaboration and analyze the trade-offs between parallelization and close collaboration. These findings inform the design of shared interaction techniques to support collaboration on wall-sized displays.

The advent of ultra-high resolution wall-size displays and their use for complex tasks require a more systematic analysis and deeper understanding of their advantages and drawbacks compared with desktop monitors. While previous work has mostly addressed search, visualization and sense-making tasks, we have designed an abstract classification task that involves explicit data manipulation. Based on our observations of real uses of a wall display, this task represents a large category of applications. We report on a controlled experiment that uses this task to compare physical navigation in front of a wall-size display with virtual navigation using pan-and-zoom on the desktop. Our main finding is a robust interaction effect between display type and task difficulty: while the desktop can be faster than the wall for simple tasks, the wall gains a sizable advantage as the task becomes more difficult. A follow-up study shows that other desktop techniques (overview+detail, lens) do not perform better than pan-and-zoom and are therefore slower than the wall for difficult tasks.

Triggering commands on large interactive surfaces is less efficient than on desktop PCs. It requires either large physical movements to reach an interaction area (e.g., buttons) or additional operations to call context menus (e.g., dwell). There is a lack of efficient ways to trigger shortcuts. We introduce Kolibri - a pen-based gesture system that allows fast access of commands on interactive whiteboards. Users can draw tiny gestures (approx. 3 mm) anywhere on the surface to trigger commands without interfering with normal inking. This approach does neither require entering a gesture mode, nor dedicated gesture areas. The implementation relies on off-the-shelf hardware only. We tested the feasibility and explored the properties of this technique with several studies. The results from a controlled experiment show significant benefits of Kolibri comparing to an existing approach.

Augmented Reality (AR) has been proved useful to guide operational tasks in professional domains by reducing the shift of attention between instructions and physical objects. Modern smartphones make it possible to use such techniques in everyday tasks, but raise new challenges for the usability of AR in this context: small screen, occlusion, operation "through a lens". We address these problems by adding real-time feedback to the AR overlay. We conducted a controlled experiment comparing AR with and without feedback, and with standard textual and graphical instructions. Results show significant benefits for mobile AR with feedback and reveals some problems with the other techniques.