arXiv preprints from January 1, 2026 through September 23, 2026 — 18:59:16 EST
Teaching software development basics to hundreds of students in a frontal setting is cost-efficient and thus still common in universities. However, in a large lecture hall, students can easily get bored, distracted, and disengaged. The frontal setting can also frustrate lecturers since interaction opportunities are limited and hard to...
When training machine learning (ML) models for potential deployment in a healthcare setting, it is essential to ensure that they do not replicate or exacerbate existing healthcare biases. Although many definitions of fairness exist, we focus on path-specific causal fairness, which allows us to better consider the social and medical...
Lazy evaluation is a powerful technique that can optimize code execution by deferring evaluations until their results are required, thus enhancing efficiency. In most modern programming languages, like R, lazy evaluation is commonly applied to function arguments. However, the application of lazy evaluation in SAS has not been...
Introduction: Socially assistive robots hold promise for enhancing therapeutic engagement in paediatric clinical settings. However, their successful implementation requires not only technical robustness but also context-sensitive, co-designed solutions. This paper presents Mobirobot, a socially assistive robot developed to support...
Many Ethereum smart contracts rely on block attributes such as block.timestamp or blockhash to generate random numbers for applications like lotteries and games. However, these values are predictable and miner-manipulable, creating the Bad Randomness vulnerability (SWC-120) that has led to real-world exploits. Current detection tools...
Evaluating personality traits in Large Language Models (LLMs) is key to model interpretation, comparison, and responsible deployment. However, existing questionnaire-based evaluation methods exhibit limited stability and offer little explainability, as their results are highly sensitive to minor variations in prompt phrasing or...
Following code style conventions in software projects is essential for maintaining overall code quality. Adhering to these conventions improves maintainability, understandability, and extensibility. Additionally, following best practices during software development enhances performance and reduces the likelihood of errors. This paper...
In this work, we provide a new convergence theory for plug-and-play proximal gradient descent (PnP-PGD) under prior mismatch where the denoiser is trained on a different data distribution to the inference task at hand. To the best of our knowledge, this is the first convergence proof of PnP-PGD under prior mismatch. Compared with the...
Effective retrieval across both seen and unseen categories is crucial for modern image retrieval systems. Retrieval on seen categories ensures precise recognition of known classes, while retrieval on unseen categories promotes generalization to novel classes with limited supervision. However, most existing deep hashing methods are...
We establish a lower bound on the eluder dimension of generalised linear model classes, showing that standard eluder dimension-based analysis cannot lead to first-order regret bounds. To address this, we introduce a localisation method for the eluder dimension; our analysis immediately recovers and improves on classic results for...
Latent diffusion models such as Stable Diffusion 1.5 offer strong generative priors that are highly valuable for image restoration, yet their full pipelines remain too computationally heavy for deployment on edge devices. Existing lightweight variants predominantly compress the denoising U-Net or reduce the diffusion trajectory, which...
Despite recent advancements in Large Language Models (LLMs), complex Software Engineering (SE) tasks require more collaborative and specialized approaches. This concept paper systematically reviews the emerging paradigm of LLM-based multi-agent systems, examining their applications across the Software Development Life Cycle (SDLC),...
In this Article, I explore the impending conflict between the protection of civil rights and artificial intelligence (AI). While both areas of law have amassed rich and well-developed areas of scholarly work and doctrinal support, a growing body of scholars are interrogating the intersection between them. This Article argues that the...
Background: Pneumonia remains a leading cause of morbidity and mortality among children worldwide, emphasizing the need for accurate and efficient diagnostic support tools. Deep learning has shown strong potential in medical image analysis, particularly for chest X-ray interpretation. This study compares two state-of-the-art...
Accurately localizing 3D objects like pedestrians, cyclists, and other vehicles is essential in Autonomous Driving. To ensure high detection performance, Autonomous Vehicles complement RGB cameras with LiDAR sensors, but effectively combining these data sources for 3D object detection remains challenging. We propose LCF3D, a novel...
Organizations and enterprises across domains such as healthcare, finance, and scientific research are increasingly required to extract collective intelligence from distributed, siloed datasets while adhering to strict privacy, regulatory, and sovereignty requirements. Federated Learning (FL) enables collaborative model building...
Variable scoping dictates how and where variables are accessible within programming languages, playing a crucial role in code efficiency and organization. This paper examines the distinct scoping rules in SAS and R, focusing on SAS's dynamic scoping and R's lexical scoping. In SAS, dynamic scoping utilizes symbol tables, resolving...
This work presents an end-to-end pipeline for generating, refining, and evaluating adversarial patches to compromise facial biometric systems, with applications in forensic analysis and security testing. We utilize FGSM to generate adversarial noise targeting an identity classifier and employ a diffusion model with reverse diffusion...
Modern logical reasoning with LLMs primarily relies on employing complex interactive frameworks that decompose the reasoning process into subtasks solved through carefully designed prompts or requiring external resources (e.g., symbolic solvers) to exploit their strong logical structures. While interactive approaches introduce...
Vision-Language-Action (VLA) tasks require reasoning over complex visual scenes and executing adaptive actions in dynamic environments. While recent studies on reasoning VLAs show that explicit chain-of-thought (CoT) can improve generalization, they suffer from high inference latency due to lengthy reasoning traces. We propose...
Transformer-based language models often achieve strong results on mathematical reasoning benchmarks while remaining fragile on basic numerical understanding and arithmetic operations. A central limitation is that numbers are processed as symbolic tokens whose embeddings do not explicitly encode numerical value, leading to systematic...
Code generation tasks aim to automate the conversion of user requirements into executable code, significantly reducing manual development efforts and enhancing software productivity. The emergence of large language models (LLMs) has significantly advanced code generation, though their efficiency is still impacted by certain inherent...
We already know that several problems like the inequivalence of P and EXP as well as the undecidability of the acceptance problem and halting problem relativize. However, relativization is a limited tool which cannot separate other complexity classes. What has not been proven explicitly is whether the Turing-recognizability of the...
Segment Anything 3 (SAM3) has established a powerful foundation that robustly detects, segments, and tracks specified targets in videos. However, in its original implementation, its group-level collective memory selection is suboptimal for complex multi-object scenarios, as it employs a synchronized decision across all concurrent...
3D human pose estimation from sparse multi-view camera rigs is an essential task for numerous applications, including action recognition, sports analysis, and human-robot interaction. While learned methods dominate the field on benchmarks, they require large annotated datasets; training-free optimization-based methods remain promising...