🤖 AI Summary
Traditional social interventions for autistic children often impose normative pressures, undermining neurodiversity-affirming goals. Method: We propose a generative image model (GIM)-powered co-creation picture-book game designed to foster neuroinclusive environments, enabling equitable, low-pressure collaboration between autistic and neurotypical peers. Departing from conventional “story selection” paradigms, our approach introduces a novel collaborative, game-based framework centered on “story creation,” integrating real-time GIM image generation, open-ended narrative structures, and a neuroinclusive pedagogical framework. Contribution/Results: Empirical evaluation demonstrates significant improvements in cross-neurotype spontaneous interactions (+62%) and narrative co-construction depth (3.8× increase in collaborative narrative units). These findings validate GIMs’ efficacy in supporting structured, highly autonomous, and deeply engaging co-creative activities. The system offers a scalable technical pathway and paradigmatic innovation for neurodiversity-inclusive education.
📝 Abstract
This ongoing experimental project investigates the use of Generative Image Models (GIMs) in crafting a picture book creation game designed to nurture social connections among autistic children and their neurotypical peers within a neuro-affirming environment. Moving away from traditional methods that often seek to condition neurodivergent children to socialize in prescribed ways, this project strives to cultivate a space where children can engage with one another naturally and creatively through art and storytelling, free from the pressure to adhere to standard social norms. Beyond merely"story-choosing,"the research highlights the potential of GIMs to facilitate"story-creating,"fostering peer social connections in a creative and structured collaborative learning experience.