Related papers: Architecture-Aware Explanation Auditing for Indust…

The escalating integration of machine learning in high-stakes fields such as healthcare raises substantial concerns about model fairness. We propose an interpretable framework - Fairness-Aware Interpretable Modeling (FAIM), to improve model…

Autonomous inspection robots for monitoring industrial sites can reduce costs and risks associated with human-led inspection. However, accurate readings can be challenging due to occlusions, limited viewpoints, or unexpected environmental…

Explainable artificial intelligence is increasingly employed to understand the decision-making process of deep learning models and create trustworthiness in their adoption. However, the explainability of Monocular Depth Estimation (MDE)…

Predictive models for student dropout, while often accurate, frequently rely on opportunistic feature sets and suffer from undocumented data leakage, limiting their explanatory power and institutional usefulness. This paper introduces a…

We develop a rigorous framework for deterministic coreset construction in empirical risk minimization (ERM). Our central contribution is the Adaptive Deterministic Uniform-Weight Trimming (ADUWT) algorithm, which constructs a coreset by…

Explanation mechanisms are increasingly used to support transparency and trust in vision-language models (VLMs), particularly in settings where model decisions require human oversight. However, the robustness of these explanations remains…

Neural Architecture Search is a costly practice. The fact that a search space can span a vast number of design choices with each architecture evaluation taking nontrivial overhead makes it hard for an algorithm to sufficiently explore…

How interpretable are the features of leading vision models? The question is increasingly pressing as these models move from research benchmarks into high-stakes deployments, yet existing methods cannot answer it reliably. We close this gap…

The rapid advancement of photorealistic Text-to-Video (T2V) generation brings in an urgent need for up-to-date evaluation methods. Existing benchmarks largely overlooked implausible scenarios and do not measure audio-visual alignment. We…

Inspection of insulators is important to ensure reliable operation of the power system. Deep learning is being increasingly exploited to automate the inspection process by leveraging object detection models to analyse aerial images captured…

Audio provides critical situational cues, yet current Audio Language Models (ALMs) face an attention bottleneck in long-form recordings where dominant background patterns can dilute rare, salient events. We introduce NAACA, a training-free…

The quality of diabetic retinopathy (DR) screening relies on the ability to correctly grade severity; however, many deep-learning (DL) classifiers cannot be easily interpreted in the clinical context. This study presents a methodology that…

Distributed denial-of-service (DDoS) attacks threaten the availability of Internet of Things (IoT) infrastructures, particularly under resource-constrained deployment conditions. Although transfer learning models have shown promising…

Explainability is a highly demanded requirement for applications in high-risk areas such as medicine. Vision Transformers have mainly been limited to attention extraction to provide insight into the model's reasoning. Our approach combines…

This paper presents a novel attention-based neural network for structured reconstruction, which takes a 2D raster image as an input and reconstructs a planar graph depicting an underlying geometric structure. The approach detects corners…

Accurate spatial prediction of power integrity issues, such as IR drop, is critical for reliable VLSI design. However, traditional simulation-based solvers are computationally expensive and difficult to scale. We address this challenge by…

Improving energy efficiency in residential buildings is critical to combating climate change and reducing greenhouse gas emissions. Retrofitting existing buildings, which contribute a significant share of energy use, is therefore a key…

Bayesian finite mixture models can identify discrete risk clusters (low-risk vs. high-risk equipment), but face three critical bottlenecks: (1) insufficient degradation signals from coarse state discretization, (2) unstable cluster…

Vision-language models (VLMs) generate fluent causal explanations, but current evaluations cannot distinguish linguistic plausibility from faithful causal reasoning. We introduce a dual-probe methodology that isolates these properties. The…

Which categories of explanation content are relevant for users of industrial AI systems, and how can those categories be organized for local, post-hoc explanations? To address these questions, a hybrid inductive-deductive qualitative…