Related papers: ScreenAudit: Detecting Screen Reader Accessibility…
Mobile applications (apps) have become an essential part of everyday life, offering convenient access to services such as banking, healthcare, and shopping. With these apps handling sensitive personal and financial data, ensuring their…
Enterprises are always on the lookout for tools that analyze end-users perspectives on their products. In particular, app reviews have been assessed as useful for guiding improvement efforts and software evolution, however, developers find…
Methods for scoring text readability have been studied for over a century, and are widely used in research and in user-facing applications in many domains. Thus far, the development and evaluation of such methods have primarily relied on…
Large language models (LLMs) have exhibited impressive capabilities in comprehending complex instructions. However, their blind adherence to provided instructions has led to concerns regarding risks of malicious use. Existing defence…
Mobile devices and platforms have become an established target for modern software developers due to performant hardware and a large and growing user base numbering in the billions. Despite their popularity, the software development process…
Humans solve problems by executing targeted plans, yet large language models (LLMs) remain unreliable for structured workflow execution. We propose RunAgent, a multi-agent plan execution platform that interprets natural-language plans while…
We introduce ASPECTSIM, a simple and interpretable framework that requires conditioning document similarity on an explicitly specified aspect, which is different from the traditional holistic approach in measuring document similarity.…
Individuals with fine motor impairments, such as those caused by conditions like Parkinson's disease, cerebral palsy, or dyspraxia, face significant challenges in interacting with traditional computer interfaces. Historically, scripted…
Achieving accessibility compliance is extremely important for many government agencies and businesses who wish to improve services for their consumers. With the growing reliance on dynamic web applications many organizations are finding it…
The increasing prevalence of large language models (LLMs) has significantly advanced text generation, but the human-like quality of LLM outputs presents major challenges in reliably distinguishing between human-authored and LLM-generated…
Large Language Models (LLMs) can now solve entire exams directly from uploaded PDF assessments, raising urgent concerns about academic integrity and the reliability of grades and credentials. Existing watermarking techniques either operate…
Despite the continued research and progress in building secure systems, Android applications continue to be ridden with vulnerabilities, necessitating effective detection methods. Current strategies involving static and dynamic analysis…
The Graphical User Interface (GUI) is pivotal for human interaction with the digital world, enabling efficient device control and the completion of complex tasks. Recent progress in Large Language Models (LLMs) and Vision Language Models…
Large language models (LLMs) have demonstrated an impressive ability to generate codes on competitive programming tasks. However, with limited sample numbers, LLMs still suffer from poor accuracy. Inspired by the process of human…
Recent advances in multimodal large language models (MLLMs) have demonstrated strong capabilities in understanding general visual content. However, these general-domain MLLMs perform poorly in face perception tasks, often producing…
The impressive essay writing and problem-solving capabilities of large language models (LLMs) like OpenAI's ChatGPT have opened up new avenues in education. Our goal is to gain insights into the widespread use of LLMs among secondary…
Mobile application marketplaces are responsible for vetting apps to identify and mitigate security risks. Current vetting processes are labor-intensive, relying on manual analysis by security professionals aided by semi-automated tools. To…
The majority of blindness is preventable, and is located in developing countries. While mHealth applications for retinal imaging in combination with affordable smartphone lens adaptors are a step towards better eye care access, the expert…
This contribution investigates how cross-platform development frameworks (CPDF) support the creation of mobile applications that are accessible to people with visual impairments through screen readers. We first systematically analyze…
Modern computer-use agents (CUA) must perceive a screen as a structured state, what elements are visible, where they are, and what text they contain, before they can reliably ground instructions and act. Yet, most available grounding…