Related papers: WebAccessVL: Violation-Aware VLM for Web Accessibi…
The vast majority of Web pages fail to comply with established Web accessibility guidelines, excluding a range of users with diverse abilities from interacting with their content. Making Web pages accessible to all users requires dedicated…
We propose general visual inspection model using Vision-Language Model~(VLM) with few-shot images of non-defective or defective products, along with explanatory texts that serve as inspection criteria. Although existing VLM exhibit high…
Using vision-language models (VLMs) in web development presents a promising strategy to increase efficiency and unblock no-code solutions: by providing a screenshot or a sketch of a UI, a VLM could generate the code to reproduce it, for…
Accurate rejection of sensitive or harmful visual content, i.e., harmful image guardrail, is critical in many application scenarios. This task must continuously adapt to the evolving safety policies and content across various domains and…
The increasing integration of Visual Language Models (VLMs) into AI systems necessitates robust model alignment, especially when handling multimodal content that combines text and images. Existing evaluation datasets heavily lean towards…
The HyperText Markup Language 5 (HTML5) <canvas> is useful for creating visual-centric web applications. However, unlike traditional web applications, HTML5 <canvas> applications render objects onto the <canvas> bitmap without representing…
Vision-language models (VLMs) (e.g. CLIP, LLaVA) are trained on large-scale, lightly curated web datasets, leading them to learn unintended correlations between semantic concepts and unrelated visual signals. These associations degrade…
Web accessibility remains an unresolved issue for a large part of the web content. There are many tools to detect errors automatically, but fixing those issues is still mostly a manual, slow, and costly process in which it is easy for…
Ensuring web accessibility at scale remains challenging because rule-based tools provide limited coverage while manual remediation is costly and error-prone. This paper evaluates large language model based agents, specifically Kimi K2.5,…
Individuals with intellectual disabilities often have difficulties in comprehending complex texts. While many text-to-image models prioritize aesthetics over accessibility, it is not clear how visual illustrations relate to text…
With the rapid development of web technology, more and more software applications have become web-based in the past decades. To ensure software quality and user experience, various techniques have been proposed to automatically test web…
Editing complex visual content from ambiguous or partially specified instructions remains a core challenge in vision-language modeling. Existing models can contextualize content but often fail to infer the underlying intent within a…
Recent advances in vision-language models (VLMs) have sparked growing interest in using them to automate web tasks, yet their feasibility as independent agents that reason and act purely from visual input remains underexplored. We…
Recent research suggests that Vision Language Models (VLMs) often rely on inherent biases learned during training when responding to queries about visual properties of images. These biases are exacerbated when VLMs are asked highly specific…
With the increasing need for inclusive and user-friendly technology, web accessibility is crucial to ensuring equal access to online content for individuals with disabilities, including visual, auditory, cognitive, or motor impairments.…
Training of autonomous driving systems requires extensive datasets with precise annotations to attain robust performance. Human annotations suffer from imperfections, and multiple iterations are often needed to produce high-quality…
This paper demonstrates that a progressively aligned language model can effectively bridge frozen vision encoders and large language models (LLMs). While the fundamental architecture and pre-training methods of vision encoders and LLMs have…
Detecting anomalous hazards in visual data, particularly in video streams, is a critical challenge in autonomous driving. Existing models often struggle with unpredictable, out-of-label hazards due to their reliance on predefined object…
Search engines enable the retrieval of unknown information with texts. However, traditional methods fall short when it comes to understanding unfamiliar visual content, such as identifying an object that the model has never seen before.…
Large language models (LLMs) have recently demonstrated strong capabilities in generating functional and aesthetic web interfaces directly from instructions. However, these models often replicate accessibility flaws from their training…