Collaboration has been shown to enhance creativity, leading to more innovative and effective outcomes. While previous research has explored the abilities of Large Language Models (LLMs) to serve as co-creative partners in tasks like writing poetry or creating narratives, the collaborative potential of LLMs in humor-rich and culturally nuanced domains remains an open question. To address this gap, we conducted a user study to explore the potential of LLMs in co-creating memes---a humor-driven and culturally specific form of creative expression. We conducted a user study with three groups of 50 participants each: a human-only group creating memes without AI assistance, a human-AI collaboration group interacting with a state-of-the-art LLM model, and an AI-only group where the LLM autonomously generated memes. We assessed the quality of the generated memes through crowdsourcing, with each meme rated on creativity, humor, and shareability. Our results showed that LLM assistance increased the number of ideas generated and reduced the effort participants felt. However, it did not improve the quality of the memes when humans were collaborated with LLM. Interestingly, memes created entirely by AI performed better than both human-only and human-AI collaborative memes in all areas on average. However, when looking at the top-performing memes, human-created ones were better in humor, while human-AI collaborations stood out in creativity and shareability. These findings highlight the complexities of human-AI collaboration in creative tasks. While AI can boost productivity and create content that appeals to a broad audience, human creativity remains crucial for content that connects on a deeper level.

Background Machine Learning plays an ever-growing role in everyday software. This means a paradigmatic shift in how software operators from algorithm-centered software where the developers defines the functionality to data-driven development where behavior is inferred from data.

Large language models like GPT and Codex drastically alter many daily tasks, including programming, where they can rapidly generate code from natural language or informal specifications. Thus, they will change what it means to be a programmer and how programmers act during software development. This work explores how AI assistance for code generation impacts productivity. In our user study (N=24), we asked programmers to complete Python programming tasks supported by a) an auto-complete interface using GitHub Copilot, b) a conversational system using GPT-3, and c) traditionally with just the web browser. Aside from significantly increasing productivity metrics, participants displayed distinctive usage patterns and strategies, highlighting that the form of presentation and interaction affects how users engage with these systems. Our findings emphasize the benefits of AI-assisted coding and highlight the different design challenges for these systems.

Computational notebooks like the Jupyter programming environment have been popular, particularly for developing data-driven applications. One of its main benefits is that it easily supports different programming languages with exchangeable kernels. Thus, it makes the user interface of computational notebooks broadly accessible. While their literate programming paradigm has advantages, we can use this infrastructure to make other paradigms similarly easily and broadly accessible to developers. In our work, we demonstrate how the Jupyter infrastructure can be utilized with different interfaces for different programming paradigms, enabling even greater flexibility for programmers and making it easier for them to adopt different paradigms when they are most suitable. We present a prototype that adds graphical programming and a multi-paradigm editor on top of the Jupyter system. The multi-paradigm editor seamlessly combines the added graphical programming with the familiar notebook interface side-by-side, which can further help developers switch between programming paradigms when desired. A subsequent user evaluation demonstrates the benefits not only of alternate interfaces and paradigms but also of the flexibility of seamlessly switching between them. Finally, we discuss some of the challenges in implementing these systems and how these can enhance the software development process in the future.

Tangible technology provides opportunities to design collaborative interactions which allow children to engage in highly collaborative activities. Unfortunately, there are few guidelines on structuring children’s interdependent collaboration with tangible technologies. In this study, we designed and developed a tangible game named MemorINO to “force” children to collaborate. We conducted a classroom study with 23 children and 3 kindergarten teachers. Our investigation revealed two main findings: (1) We could design interactive constraints with tangible technologies to “force” children to attend collaborative activities naturally and interdependently; (2) Tangible environments could help children have good engagements, especially for similar-age group children. Our findings could provide practical guidance on designing tangible interfaces to help children learn to collaborate.

Tangible learning has received increasing attention. However, in the recent decade, it has no comprehensive overview. This study aimed to fill the gap and reviewed 92 publications from all the TEI conference proceedings (2007–2021). We analysed previous studies’ characteristics (e.g., study purpose and interactive modalities) and elaborated on three common topics: collaborative tangible learning, tangibles’ impacts on learning, and comparisons between tangibles and other interfaces. Three key findings were: (1) Tangibles impacted learning because it could scaffold learning, change learning behaviour, and improve learning emotion; (2) We should see the effectiveness of tangibles with rational and critical minds. (3) Some studies emphasised too much on the interaction of tangibles and ignored their metaphor meanings. For future work, we suggest avoiding an intensive cluster on collaboration and children and consider other valuable areas, e.g., tangibles for teachers, tangibles’ social and emotional impacts on students, tangible interaction’s meaning and metaphor.

Creativity is an important part of children’s education. Tangible User Interfaces (TUIs) provide new possibilities for creative learning. In this review, we gave an overview of recent studies that supported children’s creative learning using TUIs. Results showed that TUIs had many advantages, such as they (1) were novice-friendly, (2) supported children’s cognitive process and development, (3) promoted their initiatives, (4) enabled them to think outside the box, and (5) encouraged communication and collaboration in an authentic context. Meanwhile, we summarized previous work’s three main limitations: First, most of the studies did not have a long-term experimental verification with sufficient sample size and objective evaluation; Second, some TUI designs lacked a balance of abstractness, openness, richness, and complexity; Finally, the use of TUIs had little consideration of the teacher’s role. Therefore, further research should focus more on the trans-disciplinary nature of TUIs for creative learning and leverage collaboration between human-computer interaction researchers and school teachers.

The purpose of image restoration is to recover the original state of damaged images. To overcome the disadvantages of the traditional, manual image restoration process, like the high time consumption and required domain knowledge, automatic inpainting methods have been developed. These methods, however, can have limitations for complex images and may require a lot of input data. To mitigate those, we present "interactive Deep Image Prior", a combination of manual and automated, Deep-Image-Prior-based restoration in the form of an interactive process with the human in the loop. In this process a human can iteratively embed knowledge to provide guidance and control for the automated inpainting process. For this purpose, we extended Deep Image Prior with a user interface which we subsequently analyzed in a user study. Our key question is whether the interactivity increases the restoration quality subjectively and objectively. Secondarily, we were also interested in how such a collaborative system is perceived by users.