A Constructed Response: Designing and Choreographing Robot Arm Movements in Collaborative Dance ImprovisationIn dance, dancers improvise and choreograph with each other, prototyping movement designs with each other. These interactions extend into collaboration with technology to enhance the creative process. We want to understand how dancers design and improvise movements together in the case of working with a robotic arm, which serves as an instrument in the stage space capable of non-humanoid movements. We engaged and observed dancers in a workshop to co-create movements with robots in one-human-to-one-robot and three-human-to-one-robot settings. We found that dancers produced more fluid movements in one-to-one scenarios, experiencing a stronger sense of connection and presence with the robot as a co-dancer. Conversely, in three-to-one scenarios, the dancers divided their attention between the human dancers and the robot, resulting in increased perceived use of space and more stop-and-go movements, perceiving the robot as part of the stage background. This work highlights how technologies can drive creativity in movement artists as they adapt to new ways of working with instruments, extending prior research on dancing with inanimate objects by exploring how robotic arms influence creative collaboration. We contribute insights into designing systems that support improvisational processes and artistic collaborations with non-humanoid agents.2025XCXiaoyu CHANG et al.Games, Entertainment, & CultureCSCW
"Should I choose a smaller model?'': Understanding ML Model Selection and Its Impact on SustainabilityThe increasing accessibility of large machine learning (ML) models has resulted in their widespread adoption in everyday products, with a correspondingly negative environmental impact. Selecting more suitable ML models could not only improve training time and achievable accuracy, but also long-term sustainability. However, ML developers' model selection process remains underexplored, especially with respect to sustainability trade-offs. Our interviews with 13 ML developers showed that participants select models mainly based on familiarity, accuracy and interpretability, but often overlook sustainability. They critically reflected on the current trends of large models and the lack of available information regarding model sustainability. We present implications for the ML and HCI communities, emphasizing the importance of critical reflection on model selection in education and practice. Based on our insights, we provide initial recommendations for promoting model sustainability evaluation and how the HCI community can assist in making sustainable model alternatives more accessible.2025ECEya Ben chaaben et al.Inria Paris Saclay, ExSituAI-Assisted Decision-Making & AutomationSustainable HCIEcological Design & Green ComputingCHI
FusAIn: Composing Generative AI Visual Prompts Using Pen-based InteractionAlthough current generative AI (GenAI) enables designers to create novel images, its focus on text-based and whole-image interaction limits expressive engagement with visual materials. Based on the design concept of deconstruction and reconstruction of digital visual attributes for visual prompts, we present FusAIn, a GenAI prompt composition tool that lets designers create personalized pens by loading them with objects or attributes such as color or texture. GenAI then fuses the pen's contents to create new images. Extracting and reusing inspirational material matches designers' existing work practices, making GenAI more contextualized for professional design. A study with 12 designers shows how FusAIn improves their ability to define visual details at different levels that are difficult to express with current GenAI prompts. Pen-based interaction lets them maintain fine-grained control over generated results, increasing GenAI image's editability and reusability. We discuss the benefits of "composition as prompts" and directions for future research.2025XPXiaohan Peng et al.Université Paris-Saclay, CNRS, Inria, ExSitu, LISNGenerative AI (Text, Image, Music, Video)CHI
Lost in Magnitudes: Exploring Visualization Designs for Large Value RangesWe explore the design of visualizations for values spanning multiple orders of magnitude; we call them Orders of Magnitude Values (OMVs). Visualization researchers have shown that separating OMVs into two components, the mantissa and the exponent, and encoding them separately overcomes limitations of linear and logarithmic scales. However, only a small number of such visualizations have been tested, and the design guidelines for visualizing the mantissa and exponent separately remain under-explored. To initiate this exploration, better understand the factors influencing the effectiveness of these visualizations, and create guidelines, we adopt a multi-stage workflow. We introduce a design space for visualizing mantissa and exponent, systematically generating and qualitatively evaluating all possible visualizations within it. From this evaluation, we derive guidelines. We select two visualizations that align with our guidelines and test them using a crowdsourcing experiment, showing they facilitate quantitative comparisons and increase confidence in interpretation compared to the state-of-the-art.2025KBKaterina Batziakoudi et al.Berger-Levrault; Inria, AvizInteractive Data VisualizationTime-Series & Network Graph VisualizationVisualization Perception & CognitionCHI
When Should I Lead or Follow: Understanding Initiative Levels in Human-AI Collaborative GameplayDynamics in Human-AI interaction should lead to more satisfying and engaging collaboration. Key open questions are how to design such interactions and the role personal goals and expectations play. We developed three AI partners of varying initiative (leader, follower, shifting) in a collaborative game called Geometry Friends. We conducted a within-subjects experiment with 60 participants to assess personal AI partner preference and performance satisfaction as well as perceived warmth and competence of AI partners. Results show that AI partners following human initiative are perceived as warmer and more collaborative. However, some participants preferred AI leaders for their independence and speed, despite being seen as less friendly. This suggests that assigning a leadership role to the AI partner may be suitable for time-sensitive scenarios. We identify design factors for developing collaborative AI agents with varying levels of initiative to create more effective human-AI teams that consider context and individual preference.2024ILInês Lobo et al.Generative AI (Text, Image, Music, Video)Creative Collaboration & Feedback SystemsDIS
DesignPrompt: Using Multimodal Interaction for Design Exploration with Generative AIVisually oriented designers often struggle to create effective generative AI (GenAI) prompts. A preliminary study identified specific issues in composing and fine-tuning prompts, as well as needs in accurately translating intentions into rich input. We developed DesignPrompt, a moodboard tool that lets designers combine multiple modalities — images, color, text — into a single GenAI prompt and tweak the results. We ran a comparative structured observation study with 12 professional designers to better understand their intent expression, expectation alignment and transparency perception using DesignPrompt and text input GenAI. We found that multimodal prompt input encouraged designers to explore and express themselves more effectively. Designer’s interaction preferences change according to their overall sense of control over the GenAI and whether they are seeking inspiration or a specific image. Designers developed innovative uses of DesignPrompt, including developing elaborate multimodal prompts and creating a multimodal prompt pattern to maximize novelty while ensuring consistency.2024XPXiaohan Peng et al.Generative AI (Text, Image, Music, Video)Graphic Design & Typography ToolsCreative Collaboration & Feedback SystemsDIS
PITAS: Sensing and Actuating Embedded Robotic Sheet for Physical Information CommunicationThis work presents PITAS, a thin-sheet robotic material composed of a reversible phase transition actuating layer and a heating/sensing layer. The synthetic sheet material enables non-expert makers to create shape-changing devices that can locally or remotely convey physical information such as shape, color, texture and temperature changes. PITAS sheets can be manipulated into various 2D shapes or 3D geometries using subtractive fabrication methods such as laser, vinyl, or manual cutting or an optional additive 3D printing method for creating 3D objects. After describing the design of PITAS, this paper also describes a study conducted with thirteen makers to gauge the accessibility, design space, and limitations encountered when PITAS is used as a soft robotic material while designing physical information communication devices. Lastly, this work reports on the results of a mechanical and electrical evaluation of PITAS and presents application examples to demonstrate its utility.2022TCTingyu Cheng et al.Interactive Computing, Interactive ComputingShape-Changing Interfaces & Soft Robotic MaterialsShape-Changing Materials & 4D PrintingCHI
KeyTch: Combining the Keyboard with a Touchscreen for Rapid Command Selection on ToolbarsIn this paper, we address the challenge of reducing mouse pointer transitions from the working object (e.g. text document) to simple or multi-level toolbars on desktop computers. To this end, we introduce KeyTch (pronounced ‘Keetch’), a novel approach for command selection on toolbars based on the combined use of the keyboard with a touchscreen. The toolbar is displayed on the touchscreen, which is positioned below the keyboard. Users can select commands by performing gestures combining a key press with the pinky finger, and a screen touch with the thumb of the same hand. After analyzing the design properties of KeyTch, a preliminary experiment validates that users can perform such gestures and reach the entire touchscreen surface with the thumb. Then a first user study unveils that direct touch outperforms indirect pointing to reach items on a simple toolbar displayed on the touchscreen. In a second study, we validate that KeyTch interaction techniques outperform the mouse for selecting items on a multi-level toolbar displayed on the touchscreen, allowing to select up to 720 commands with an accuracy above 95%, or 480 commands with an accuracy above 97%. Finally, two follow-up studies validate the benefits of KeyTch when used in a more integrated context.2021EKElio Keddisseh et al.Universite Paul Sabatier, Oktal SydacFoot & Wrist InteractionKnowledge Worker Tools & WorkflowsCHI
An Exploratory Study on Visual Exploration of Model Simulations by Multiple Types of ExpertsExperts in different domains rely increasingly on simulation models of complex processes to reach insights, make decisions, and plan future projects. These models are often used to study possible trade-offs, as experts try to optimise multiple conflicting objectives in a single investigation. Understanding all the model intricacies, however, is challenging for a single domain expert. We propose a simple approach to support multiple experts when exploring complex model results. First, we reduce the model exploration space, then present the results on a shared interactive surface, in the form of a scatterplot matrix and linked views. To explore how multiple experts analyse trade-offs using this setup, we carried out an observational study focusing on the link between expertise and insight generation during the analysis process. Our results reveal the different exploration strategies and multi-storyline approaches that domain experts adopt during trade-off analysis, and inform our recommendations for collaborative model exploration systems.2019NBNadia Boukhelifa et al.UMR GMPA, AgroParisTech, INRA, Univ. Paris-SaclayInteractive Data VisualizationUser Research Methods (Interviews, Surveys, Observation)CHI
Automation: Danger or Opportunity? Designing and Assessing Automation for Interactive SystemsThis course takes a practical approach to introduce the principles, methods and tools in task modeling and how this technique can support identification of automation opportunities, dangers and limitations. A technical interactive hands-on exercise of how to "do it right", such as: How to go from task analysis to task models? How to identify tasks that are good candidate for automation (through analysis and simulation)? How to identify reliability and usability dangers added by automation? How to design usable automation at system, application and interaction levels? And more...2018PPPhilippe Palanque et al.ICS-IRIT, Université Paul Sabatier Toulouse 3AI-Assisted Decision-Making & AutomationImpact of Automation on WorkCHI
Taking into account Sensory Knowledge: the case of Geo-techologies for children with visual impairmentsThis paper argues for designing geo-technologies supporting non-visual sensory knowledge. Sensory knowledge refers to the implicit and explicit knowledge guiding our uses of our senses to understand the world. To support our argument, we build on an 18 months field-study on geography classes for primary school children with visual impairments. Our findings show (1) a paradox in the use of non-visual sensory knowledge: described as fundamental to the geography curriculum, it is mostly kept out of school; (2) that accessible geo-technologies in the literature mainly focus on substituting vision with another modality, rather than enabling teachers to build on children's experiences; (3) the importance of the hearing sense in learning about space. We then introduce a probe, a wrist-worn device enabling children to record audio cues during field-trips. By giving importance to children's hearing skills, it modified existing practices and actors' opinions on non-visual sensory knowledge. We conclude by reflecting on design implications, and the role of technologies in valuing diverse ways of understanding the world.2018EBEmeline Brulé et al.CNRS i3Visual Impairment Technologies (Screen Readers, Tactile Graphics, Braille)Geospatial & Map VisualizationCHI