Generative AI technologies have introduced a paradigm shift in machine learning and are rapidly being adopted by consumers and enterprises alike. Consumer applications like ChatGPT, DALL-E, and Midjourney are making access to these technologies widely available and have fueled the rapid commercialization of generative AI. At the same time, generative models have enabled a radically new way for people to interact with computing technology by allowing them to specify what they want rather than how it should be produced. Users are able to create specifications of the kinds of outputs they desire in natural language, through sketches and gestures, novel UI controls or other means. In a recent article, Nielsen called this form of interaction intent-based outcome specification. He argues that it is the first new interaction paradigm in 60 years, fundamentally different from batch processing and command-based interaction. Intent-based outcome specification shifts control over how computation is performed from the user towards the generative AI models, enabling new forms of co-creativity and co-creation while also creating new challenges of how to best support users with creating outcome specifications that yield the desired results and are effective and safe to use.
The central questions of our workshop are:
- How do we design, implement, and evaluate intent-based co-creative experiences that enhance human creativity in their work, play, and education across a range of media types (text, images, audio, code, and video)?
- How will user needs for creativity support drive the development of generative AI algorithms? How can the capabilities of generative models be leveraged for positive and effective co-creative user experiences?
The goal of our workshop is to bring together researchers and practitioners from the domains of HCI & AI to establish a joint community to deepen our understanding of the human-AI co-creative process and to explore the opportunities and challenges of creating meaningful, effective and safe user experiences for intent-based generative systems. Submissions are encouraged, but not limited to, the following topics:
- Novel, AI-augmented user experiences across a range of media types (text, images, audio, code, and video) that support the creation of physical and/or digital artifacts
- Novel ways for creating, managing, and interacting with outcome specifications
- Use cases & novel applications for co-creativity including business use cases
- Techniques, methodologies, & algorithms that enable new user experiences and interactions with generative models and allow for directed and purposeful manipulation of the model output
- Usage patterns, design guidelines, and design principles for intent-based outcome specification that support effective and safe use
- Issues of governance, privacy, and ownership of AI-generated or human-AI co-created content
- Security, including forensic tools and approaches for deep fake detection
- Evaluations of human-AI co-creative processes and quality metrics of AI-generated or human-AI co-created content
- User research on needs & algorithmic requirements for co-creative systems, perceptions of human-AI co-creative systems, trust of co-creative tools & artifacts, and/or implications for HCI theories
- Lessons learned from computational art & design and generative design, and how these impact research
- Potential risks and harms of working with generative models and generated content, and strategies to detect or mitigate those harms
All papers will undergo a single-blind peer review (i.e. author names and affiliations should be listed). If accepted, at least one of the authors must attend the workshop to present the work.
A workshop summary will be included in the ACM Digital Library for IUI 2024. Although papers and demos are not part of the archival ACM IUI proceedings, the papers and demos accepted at IUI workshops 2024 will be published in common proceedings via CEUR-WS (see https://ceur-ws.org/Vol-3359/ for last year’s workshop proceedings).
Papers & Demos
Please follow the CEUR guidelines for the single column paper template (download the CEUR template. The length should be no less than 5 pages for papers and demos, and no more than 10 maximum to be published in CEUR (see https://ceur-ws.org/HOWTOSUBMIT.html for details).
Posters
We also encourage submissions of non-archival, extended abstracts for our poster session. Note that those abstracts will not be published in CEUR. The length should be two pages and follow the same CEUR guidelines outlined above.
Please submit your papers, demos, and poster abstracts to EasyChair by January 16, 2024: https://easychair.org/my/conference?conf=haigen2024