Jul 9: Workshop proceedings have been published in CEUR: http://ceur-ws.org/Vol-2903/.
Workshop Description
Recent advances in generative AI through deep learning approaches such as generative adversarial networks (GANs), variational autoencoders (VAEs), and language models will enable new kinds of user experiences around content creation. These advances have enabled content to be produced with an unprecedented level of fidelity. Goodfellow’s work on face generation and StyleGan, OpenAI’s GPT-3 model, and recent deep fake videos of Mark Zuckerberg and Bill Gates are all prominent examples of the state of the art in the generation of text, image, and video content. In many cases, content generated by generative models is either indistinguishable from human-generated content or could not be produced by human hands. These examples also highlight some of the significant societal, ethical, and organizational challenges generative AI is posing around issues such as security, privacy, ownership, quality metrics, and evaluation of generated content.
While the areas of computational creativity, generative design, and computational art have existed for some time these communities have not been grounded at the intersection of generative deep learning approaches and human-computer interaction.
Goals
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 powerful user experiences with deep generative models. We envision that the user experience of creating both physical and digital artifacts will become a partnership between people and AI: people will take the role of specification, goal setting, steering, high-level creativity, curation, and governance, whereas AI will augment human abilities through inspiration, creativity, low-level detail work, and the ability to design at scale.
The central question of our workshop is how can we build co-creative systems that make people feel that they have “creative superpowers”? How will user needs drive the development of generative AI algorithms, and how can the capabilities of generative models be leveraged to create effective co-creative user experiences?
Submissions
Submissions will take the form of short papers, long papers, and demos, following the IUI paper and demo guidelines. Please see the Call for Participation for relevant topics and submission instructions.