People with temporary disabilities encounter access barriers at work, yet often face additional challenges when selecting accessibility technologies to address their access needs: tools may require time, training, or long-term commitment that does not align with the uncertain nature of their disability [34].Compared to people with permanent or chronic conditions, they are less likely to adapt [44] or adopt customized, expensive solutions [34], despite the possibility that their disability may become permanent [4,46].Broadly available generative AI (GAI) tools are increasingly recognized for their potential as a tool to support on-demand access for work and education [21] across a range of disabilities.This experience report presents a reflection on the author's use of multimodal GAI as a low-barrier, rapid access tool during a temporary disabilityaddressing access needs that arose during an illness and impacted verbal communication, visual processing, and manual dexterity in both work and research tasks.The use of GAI to address these temporary access barriers reveals conflicting priorities in adoption and utility, and surfaces tensions between meeting immediate needs and navigating the uncertain, and sometimes unintended, continued use of these tools over time.

Tactile graphics present visual information to blind and visually-impaired individuals in an accessible way, through touch. Current methods for producing tactile graphics, such as embossing or swell-paper printing, have limitations such as durability - and the tools required to produce them are limited in expressiveness. In this project, we explore embroidery as a medium for producing tactile graphics. Embroidery, traditionally known for its variety and visual beauty, offers not just improved durability and ease of production - but the ability to convey information through a broad range of stitch types. Following an exploration of the design space of embroidered tactile graphics, we identify key perceptual properties that impact how embroidered textures are differentiated. Based on these differences, we introduce an optimization algorithm for assigning textures to regions of tactile graphics in a way that makes them diverse and legible. We implement an end-to-end pipeline for producing embroidered tactile graphics and evaluate the comprehensibility and legibility of our design with 6 blind participants. Our findings showed that embroidered tactile graphics present information accurately and comprehensively, and that measurable properties, such as the use of spacing and distinctiveness, were an important factor of expressive and legible design.

Generative AI (AI) has become ubiquitous in both daily and professional life, with emerging research demonstrating its potential as a tool for accessibility. Neurodivergent people, often left out by existing accessibility technologies, develop their own ways of navigating normative expectations. GAI offers new opportunities for access, but it is important to understand how neurodivergent "power users"-successful early adopters-engage with it and the challenges they face. Further, we must understand how marginalization and intersectional identities influence their interactions with GAI. Our autoethnography, enhanced by privacy-preserving GAI-based diaries and interviews, reveals the intricacies of using GAI to navigate normative environments and expectations. Our findings demonstrate how GAI can both support and complicate tasks like code-switching, emotional regulation, and accessing information. We show that GAI can help neurodivergent users to reclaim their agency in systems that diminish their autonomy and self-determination. However, challenges such as balancing authentic self-expression with societal conformity, alongside other risks, create barriers to realizing GAI's full potential for accessibility.

Slide deck accessibility is often studied for people who are blind or visually impaired, but rarely for other people with access needs. We first conducted focus groups with 17 people with slide deck access needs and found that their access needs differed greatly and often conflicted. Moreover, some people’s access needs changed throughout the day (e.g., needing lower contrast colors at night). Therefore, we conducted a design probe with 14 of the existing participants to understand the experience of using a plug-in that lets audience members at a presentation modify a local copy of the slides to meet their accessibility needs. We then interviewed four slide deck authors and presenters to offer a preview of the perspectives that other stakeholders of this tool might have. Finally, we created a functional prototype as a Google Slides plug-in with a subset of the features requested by the participants.

With the recent rapid rise in Generative Artificial Intelligence (GAI) tools, it is imperative that we understand their impact on people with disabilities, both positive and negative. However, although we know that AI in general poses both risks and opportunities for people with disabilities, little is known specifically about GAI in particular. To address this, we conducted a three-month autoethnography of our use of GAI to meet personal and professional needs as a team of researchers with and without disabilities. Our findings demonstrate a wide variety of potential accessibility-related uses for GAI while also highlighting concerns around verifiability, training data, ableism, and false promises.