Related papers: VA-Blueprint: Uncovering Building Blocks for Visua…
Current resources for data literacy education, such as visualization galleries and datasets, provide useful examples but lack mechanisms for learners to query, compare, and navigate the visualization design space efficiently. This position…
Datasets of visualization play a crucial role in automating data-driven visualization pipelines, serving as the foundation for supervised model training and algorithm benchmarking. In this paper, we survey the literature on visualization…
Software reliability is critical in ensuring that the digital systems we depend on function correctly. In software development, increasing software reliability often involves testing. However, for complex and critical systems, developers…
Visual question answering (VQA) is a task that combines both the techniques of computer vision and natural language processing. It requires models to answer a text-based question according to the information contained in a visual. In recent…
The efficacy of Large Vision-Language Models (LVLMs) is critically dependent on the quality of their training data, requiring a precise balance between visual fidelity and instruction-following capability. Existing datasets, however, are…
Existing benchmarks for visual question answering lack in visual grounding and complexity, particularly in evaluating spatial reasoning skills. We introduce FlowVQA, a novel benchmark aimed at assessing the capabilities of visual…
We launch EVA, a vision-centric foundation model to explore the limits of visual representation at scale using only publicly accessible data. EVA is a vanilla ViT pre-trained to reconstruct the masked out image-text aligned vision features…
Despite the rapid progress of Vision-Language Models (VLMs), their capabilities are inadequately assessed by existing benchmarks, which are predominantly English-centric, feature simplistic layouts, and support limited tasks. Consequently,…
Vision-Language-Action (VLA) models for autonomous driving show promise but falter in unstructured corner case scenarios, largely due to a scarcity of targeted benchmarks. To address this, we introduce Impromptu VLA. Our core contribution…
This report provides an architecture-led analysis of two modern vision-language models (VLMs), Qwen2.5-VL-7B-Instruct and Llama-4-Scout-17B-16E-Instruct, and explains how their architectural properties map to a practical video-to-artifact…
Systems with artificial intelligence components, so-called AI-based systems, have gained considerable attention recently. However, many organizations have issues with achieving production readiness with such systems. As a means to improve…
One of the primary challenges faced by deep learning is the degree to which current methods exploit superficial statistics and dataset bias, rather than learning to generalise over the specific representations they have experienced. This is…
Deep learning models require the configuration of many layers and parameters in order to get good results. However, there are currently few systematic guidelines for how to configure a successful model. This means model builders often have…
AI prevails in financial fraud detection and decision making. Yet, due to concerns about biased automated decision making or profiling, regulations mandate that final decisions are made by humans. Financial fraud investigators face the…
A software architect uses quality requirements to design the architecture of a system. However, it is essential to ensure that the system's final architectural design achieves the standard quality requirements. The existing architectural…
Deep learning-based website fingerprinting has emerged as an effective technique for inferring the websites users visit. Although existing methods achieve strong performance on closed-world datasets, they often fail to generalize to…
IT-security experts engage in behavior-based malware analysis in order to learn about previously unknown samples of malicious software (malware) or malware families. For this, they need to find and categorize suspicious patterns from large…
Open-vocabulary learning has emerged as a cutting-edge research area, particularly in light of the widespread adoption of vision-based foundational models. Its primary objective is to comprehend novel concepts that are not encompassed…
2D assembly diagrams are often abstract and hard to follow, creating a need for intelligent assistants that can monitor progress, detect errors, and provide step-by-step guidance. In mixed reality settings, such systems must recognize…
Recent advances in visual-language machine learning models have demonstrated exceptional ability to use natural language and understand visual scenes by training on large, unstructured datasets. However, this training paradigm cannot…