Visual artists often use critique to improve their work, but traditional feedback methods are limited by scheduling constraints, emotional difficulties, and one-size-fits-all approaches. While Artificial Intelligence (AI) systems like Multimodal Large Language Models could provide tailored and convenient feedback, existing conversational interfaces have not been optimized for this purpose. We conducted a co-design study to understand artists’ requirements and preferences for an AI feedback tool. Participants valued the objectivity and availability of an AI tool, but wanted non-intrusive guidance that preserved their sense of ownership. Such a tool must adapt to project life-cycles, maintain contextual memory, and support free-form input with spatially grounded multimodal output. Differences in AI persona preferences necessitate configurable, but “sticky”, controls. From these findings, we developed a prototype, which our participants assessed, leading to design insights and interface refinements. Our work helps inform the design process of future AI-based creativity support tools.

The uses of handheld mobile devices are diverse, yet interaction is not; touchscreens are the singular primary interface on most mobiles. Touch interaction has usability issues (e.g., the “fat fingers problem”) which impair the fine control of small interface elements, such as when working with text. Beyond text entry, this includes tasks like placing the in-text cursor (caret), text selection, and copy/paste. Current solutions for touch usability issues do not address complex uses like working with text. We propose deformable interaction, specifically bend, added alongside touch to support working with text on mobile. We explore this through a study of BendAide, a novel deformable 3D printed case for mobiles that adds bend interaction to the device. We found that people perceive different advantages between bend and touch and that they will alternate between these inputs based on task demands and their personal abilities. Adding alternate input options to mobile could reduce the complexity of on-display interfaces and interactions and give people more choice in how they use their devices.

Artificial Intelligence (AI) tools have recently gained widespread interest for image creation, but tool developers have largely focused on technical capabilities or specialized domain uses, rather than visual artists as users. We collected survey data from 89 practising visual artists and conducted follow-up interviews with 30 of them, to better understand their diverse needs and values. Through reflexive thematic analysis, we explored visual artists’ attitudes towards collaboration in art creation both with human artists and with AI- and other technology-based support systems. Our results suggest that the focus of popular AI tools on high-quality, finished images does not meet the needs of visual artists. Instead, they wanted reference images, ideation support, and variant exploration. We identified similarities and differences between how visual artists view collaboration with other artists or with machine support, enabling designers of new tools to adopt a more user-centered approach.

As more AI agents are embedded in the interactive systems of daily life, it becomes increasingly important to support both users and designers in their reasoning about how those systems work. These improved capacities can lead to both more efficient design decisions and more effective usage of such systems. In this paper, we introduce a novel software application for modelling complex interactive systems, where the capabilities and constraints of both AI and human agents are a primary focus of each model. The software provides tools to help users build, explore, and share models, which affords opportunities for both education and analysis.

With Artificial Intelligence (AI) agents becoming more commonplace across the systems that we use every day, it is becoming increasingly important to document and convey the capabilities and constraints of these agents as interactive partners. In this paper, we extend our existing method for modelling interactive systems to facilitate recording and visualizing several key aspects of human-agent interaction. These include what elements of a system can be changed, who (or what) can observe or change them, who (or what) is able to change the system’s constraints, and more.

We explore the use of graph embedding techniques to represent the player behaviour that is expressed in the logs of video games. While such logs hold data that could be useful for personalization, the data is often poorly structured for use with Artificial Intelligence systems and its dimensionality is often high. By using a graph to structure the logs and applying embedding techniques to reduce their dimensionality, a compact vector representation can be obtained that preserves some of their semantics. To explore the potential value of this approach, we obtained gameplay logs from over 3000 matches of Defense of the Ancients 2 (Dota 2) and compared 13 parameter variations of three different embedding techniques: NODE2VEC, LINE, and TGN. Our analysis considers the effects of embedded vector size, dataset size, a step size used for updating vectors as a game proceeds, and different types of player interaction. The results show that NODE2VEC outperforms the other techniques on 7 of the 13 variations that we tested, and that removing one type of player interaction can make it easier to predict the others.

Many questions remain unanswered in relation to player experience, particularly with respect to adaptive video games. To explore this topic, our research seeks to investigate how a player's awareness of an Artificial Intelligence (AI) experience manager affects their perceptions while they play a game. In this paper, we describe a first investigation of this topic, toward identifying areas that could be interesting for further study. The results of our study hint that the awareness of an AI manager might change a player's perceived self-efficacy, depending on the player's gender.