arXiv preprints from January 1, 2026 through September 9, 2026 — 08:56:37 EST
Dialectal Arabic (DA) speech data vary widely in domain coverage, dialect labeling practices, and recording conditions, complicating cross-dataset comparison and model evaluation. To characterize this landscape, we conduct a computational analysis of linguistic ``dialectness'' alongside objective proxies of audio quality on the...
Climate discourse online shapes public understanding of climate change and informs political and policy debate, yet it unfolds across structurally different environments: paid advertising platforms host targeted, institutionally produced messaging, while public social media reflects largely organic, user-driven discussion. We present...
Humans can look at a static scene and instantly predict what happens next -- will moving this object cause a collision? We call this ability Causal Spatial Reasoning. However, current multimodal large language models (MLLMs) cannot do this, as they remain largely restricted to static spatial perception, struggling to answer "what-if"...
Robustness verification of neural networks, referring to formally proving that neural networks satisfy robustness properties, is of crucial importance in safety-critical applications, where model failures can result in loss of human life or million-dollar damages. However, the dependability of verification results may be questioned...
Benchmarking large language models (LLMs) is critical for understanding their capabilities, limitations, and robustness. In addition to interface artifacts, prior studies have shown that LLM decisions can be influenced by directive signals such as social cues, framing, and instructions. In this work, we introduce option injection, a...
We propose Enginuity - the first open, large-scale, multi-domain engineering diagram dataset with comprehensive structural annotations designed for automated diagram parsing. By capturing hierarchical component relationships, connections, and semantic elements across diverse engineering domains, our proposed dataset would enable...
Resolving team conflicts requires not only task-specific competence, but also social intelligence to find common ground and build consensus. As AI agents increasingly collaborate on complex work, they must develop coordination capabilities to function as effective teammates. Yet we hypothesize that current agents lack these...
Efficient and scalable deployment of machine learning (ML) models is a prerequisite for modern production environments, particularly within regulated domains such as healthcare and pharmaceuticals. In these settings, systems must balance competing requirements, including minimizing inference latency for real-time clinical decision...
Telegram has become one of the leading platforms for disseminating misinformational messages. However, many existing pipelines still classify each message's credibility based on the reputation of its associated domain names or its lexical features. Such methods work well on traditional long-form news articles published by well-known...
Production LLM systems often rely on separate models for safety and other classification-heavy steps, increasing latency, VRAM footprint, and operational complexity. We instead reuse computation already paid for by the serving LLM: we train lightweight probes on its hidden states and predict labels in the same forward pass used for...
Increasing clinical trial protocol complexity, amendments, and challenges around knowledge management create significant burden for trial teams. Structuring protocol content into standard formats has the potential to improve efficiency, support documentation quality, and strengthen compliance. We evaluate an Artificial Intelligence...
We study the problem of allocating a set of indivisible items among agents whose preferences include externalities. Unlike the standard fair division model, agents may derive positive or negative utility not only from items allocated directly to them, but also from items allocated to other agents. Since exact envy-freeness cannot be...
Large language models (LLMs) are increasingly deployed in decision-making tasks, where not only accuracy but also reliable confidence estimates are essential. Well-calibrated confidence enables downstream systems to decide when to trust a model and when to defer to fallback mechanisms. In this work, we conduct a systematic study of...
Modeling groundwater flow in three-dimensional fractured crystalline media requires accounting for strong spatial heterogeneity induced by fractures. Fine-scale discrete fracture-matrix (DFM) simulations can capture this complexity but are computationally expensive, especially when repeated evaluations are needed. To address this, we...
Open source software (OSS) forms the backbone of industrial data workflows and enterprise systems. However, many OSS projects face operational risks due to informal or centralized governance. This paper presents a practical case study of data.table, a high-performance R package widely adopted in production analytics pipelines, which...
Graph neural networks are usually treated as auxiliaries for combinatorial optimization: they imitate algorithms, guide search, or supply scores to classical procedures. We show that this auxiliary role is not intrinsic. A GNN can itself be a heuristic. For the Euclidean Travelling Salesman Problem, we train a non-autoregressive GNN...
Humans use context to assess the veracity of information. However, current audio deepfake detectors only analyze the audio file without considering either context or transcripts. We create and analyze a Journalist-provided Deepfake Dataset (JDD) of 255 public deepfakes which were primarily contributed by over 70 journalists since...
As quantum machine-learning architectures mature, a central challenge is no longer their construction, but identifying the regimes in which they offer practical advantages over classical approaches. In this work, we introduce a framework for addressing this question in data-driven hadronic physics problems by developing diagnostic...
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...