Related papers: Architecture-Aware Explanation Auditing for Indust…
Cloud computing has become the foundation of modern digital infrastructure, yet the absence of a unified architectural and compliance framework impedes interoperability, auditability, and robust security. This paper introduces a formal,…
If a product deviates from its desired properties in the injection moulding process, its root cause analysis can be aided by models that relate the input machine settings with the output quality characteristics. The machine learning models…
Explainable Artificial Intelligence (XAI) techniques, such as Gradient-weighted Class Activation Mapping (Grad-CAM), have become indispensable for visualizing the reasoning process of deep neural networks in medical image analysis. Despite…
Intelligent anomaly detection in dynamic visual environments requires reconciling real-time performance with semantic interpretability. Conventional approaches address only fragments of this challenge. Reconstruction-based models capture…
Deep neural networks can predict human judgments, but this does not imply that they rely on human-like information or reveal the cues underlying those judgments. Prior work has addressed this issue using attribution heatmaps, but their…
This study aims to systematically evaluate the performance of large language models (LLMs) in abstract visual reasoning problems. We examined four LLM models (GPT-4.1-Mini, Claude-3.5-Haiku, Gemini-1.5-Flash, Llama-3.3-70b) utilizing four…
Visuomotor policies trained via imitation learning are capable of performing challenging manipulation tasks, but are often extremely brittle to lighting, visual distractors, and object locations. These vulnerabilities can depend…
Interpretability is essential for user trust in real-world anomaly detection applications. However, deep learning models, despite their strong performance, often lack transparency. In this work, we study the interpretability of…
General aviation fault diagnosis and efficient maintenance are critical to flight safety; however, deploying deep learning models on resource-constrained edge devices poses dual challenges in computational capacity and interpretability.…
Recent advances in visual reasoning have leveraged vision transformers to tackle the ARC-AGI benchmark. However, we argue that the feed-forward architecture, where computational depth is strictly bound to parameter size, falls short of…
Automated vulnerability detection in critical-infrastructure software confronts a fundamental barrier: industrial software is routinely deployed as stripped, symbol-free binaries that deprive conventional Software Composition Analysis of…
The interest in complex deep neural networks for computer vision applications is increasing. This leads to the need for improving the interpretable capabilities of these models. Recent explanation methods present visualizations of the…
Abstract reasoning is a cornerstone of human intelligence, and replicating it with artificial intelligence (AI) presents an ongoing challenge. This study focuses on efficiently solving Raven's progressive matrices (RPM), a visual test for…
Attention maps, a popular heatmap-based explanation method for Visual Question Answering (VQA), are supposed to help users understand the model by highlighting portions of the image/question used by the model to infer answers. However, we…
Intelligent document processing pipelines extract structured entities (tables, images, and text) from documents for use in downstream systems such as knowledge bases, retrieval-augmented generation, and analytics. A persistent limitation of…
The growing reliance on deep learning models in safety-critical domains such as healthcare and autonomous navigation underscores the need for defenses that are both robust to adversarial perturbations and transparent in their…
AI image generators create both photorealistic images and stylized art, necessitating robust detectors that maintain performance under common post-processing transformations (JPEG compression, blur, downscaling). Existing methods optimize…
While transformers achieve strong performance, their internal decision-making processes remain opaque. We investigate whether architectural constraints can enforce interpretability by design through architectural stream independence:…
Visual question answering requires high-order reasoning about an image, which is a fundamental capability needed by machine systems to follow complex directives. Recently, modular networks have been shown to be an effective framework for…
In this study, we consider the problem of generating visual explanations in visual foundation models. Numerous methods have been proposed for this purpose; however, they often cannot be applied to complex models due to their lack of…