arXiv preprints from January 1, 2026 through July 20, 2026 — 06:33:41 EST
Evaluating whether text-to-image models follow explicit spatial instructions is difficult to automate. Object detectors may miss targets or return multiple plausible detections, and simple geometric tests can become ambiguous in borderline cases. Spatial evaluation is naturally a selective prediction problem, the checker may abstain...
The rapid growth of machine learning assets has made it increasingly difficult for software engineers to identify models and datasets that match their specific needs. Browsing large registries, such as Hugging Face, is time-consuming, error-prone, and rarely tailored to Software Engineering (SE) tasks. We present MLAssetSelection, a...
Federated Learning struggles under temporal concept drift where client data distributions shift over time. We demonstrate that standard FedAvg suffers catastrophic forgetting under seasonal drift on Fashion-MNIST, with accuracy dropping from 74% to 28%. We propose client-side experience replay, where each client maintains a small...
Explaining numerical physics problems often requires more than text-based solutions; clear visual reasoning can substantially improve conceptual understanding. While large language models (LLMs) demonstrate strong performance on many physics questions in textual form, their ability to generate long, high-quality visual explanations...
This document presents a comprehensive simulation framework designed to model urban incidents involving pedestrians and vehicles. Using a multiagent systems approach, two types of agents (pedestrians and vehicles) are introduced within a 2D grid based urban environment. The environment encodes streets, sidewalks, buildings, zebra...
This paper introduces a novel framework for robotic vision-based navigation that integrates Hybrid Neural Networks (HNNs) with Spiking Neural Network (SNN)-based filtering to enhance situational awareness for unmodeled obstacle detection and localization. By leveraging the complementary strengths of Artificial Neural Networks (ANNs)...
Despite their promise, fair machine learning methods often yield Pareto-inefficient models, in which the performance of certain groups can be improved without degrading that of others. This issue arises frequently in traditional in-processing approaches such as fairness-through-regularization. In contrast, existing Pareto-efficient...
Generative AI has emerged as a transformative paradigm in engineering design, enabling automated synthesis and reconstruction of complex 3D geometries while preserving feasibility and performance relevance. This paper introduces a domain-specific implicit generative framework for turbine blade geometry using DeepSDF, addressing...
The rapid adoption of large language models (LLMs) has enabled new forms of AI-assisted reasoning across scientific, technical, and organizational domains. However, prevailing modes of LLM use remain cognitively unstructured: problem framing, knowledge exploration, retrieval, methodological awareness, and explanation are typically...
Vision-Language Models (VLMs), particularly CLIP, have revolutionized anomaly detection by enabling zero-shot and few-shot defect identification without extensive labeled datasets. By learning aligned representations of images and text, VLMs facilitate anomaly classification and segmentation through natural language descriptions of...
Open-set learning and discovery (OSLD) is a challenging machine learning task in which samples from new (unknown) classes can appear at test time. It can be seen as a generalization of zero-shot learning, where the new classes are not known a priori, hence involving the active discovery of new classes. While zero-shot learning has...
Learning profitable intraday trading policies from financial time series is challenging due to heavy noise, non-stationarity, and strong cross-sectional dependence among related assets. We propose \emph{WaveLSFormer}, a learnable wavelet-based long-short Transformer that jointly performs multi-scale decomposition and return-oriented...
Prior research demonstrates that performance of language models on reasoning tasks can be influenced by suggestions, hints and endorsements. However, the influence of endorsement source credibility remains underexplored. We investigate whether language models exhibit systematic bias based on the perceived expertise of the provider of...
The techniques used in modern attacks have become an important factor for investigation. As we advance further into the digital age, cyber attackers are employing increasingly sophisticated and highly threatening methods. These attacks target not only organizations and governments but also extend to private and corporate sectors....
In most High Performance Computing (HPC) projects nowadays, there is a lot of data obtained from different sources, depending on the project's objectives. Some of that data is very huge in terms of size, so copying such data sometimes is an unrealistic goal. On the other hand, science requires data used for different purposes to...
The Latin American Giant Observatory (LAGO) project utilizes extensive High-Performance Computing (HPC) resources for complex astroparticle physics simulations, making resource efficiency critical for scientific productivity and sustainability. This article presents a detailed analysis focused on quantifying and improving HPC resource...
Post-quantum cryptography (PQC) introduces significant computational and communication overhead, which poses challenges for resource-constrained computer systems, Internet of Things (IoT), and Industrial IoT (IIoT) devices. This paper presents an experimental evaluation of the Quantum Encryption Resilience Score (QERS) applied to...
Energy usage prediction is important for various real-world applications, including grid management, infrastructure planning, and disaster response. Although a plethora of deep learning approaches have been proposed to perform this task, most of them either overlook the essential spatial correlations across households or fail to scale...
Retinal fundus photography is indispensable for ophthalmic screening and diagnosis, yet image quality is often degraded by noise, artifacts, and uneven illumination. Recent GAN- and diffusion-based enhancement methods improve perceptual quality by aligning degraded images with high-quality distributions, but our analysis shows that...
Diffusion models have emerged as state-of-the-art generative methods for image synthesis, yet their potential as general-purpose feature encoders remains underexplored. Trained for denoising and generation without labels, they can be interpreted as self-supervised learners that capture both low- and high-level structure. We show that...
Transformers have become the foundational architecture for a broad spectrum of sequence modeling applications, underpinning state-of-the-art systems in natural language processing, vision, and beyond. However, their theoretical limitations in discrete reasoning tasks, such as arithmetic, logical inference, and algorithmic composition,...
In this study, we explore the application of deep learning techniques for predicting cleansing quality in colon capsule endoscopy (CCE) images. Using a dataset of 500 images labeled by 14 clinicians on the Leighton-Rex scale (Poor, Fair, Good, and Excellent), a ResNet-18 model was trained for classification, leveraging stratified...
Classifying points in high dimensional spaces is a fundamental geometric problem in machine learning. In this paper, we address classifying points in the $d$-dimensional Hilbert polygonal metric. The Hilbert metric is a generalization of the Cayley-Klein hyperbolic distance to arbitrary convex bodies and has a diverse range of...
Although effective teamwork and communication are critical to surgical safety, structured training for non-technical skills (NTS) remains limited compared with technical simulation. The ACS/APDS Phase III Team-Based Skills Curriculum calls for scalable tools that both teach and objectively assess these competencies during laparoscopic...
While deep neural networks are extremely effective at classifying images, they remain opaque and hard to interpret. We introduce local and global explanation methods for black-box models that generate explanations in terms of human-recognizable primitive concepts. Both the local explanations for a single image and the global...