arXiv preprints from January 1, 2026 through September 22, 2026 — 01:35:07 EST
This study investigates how YouTube content creators utilize scientific evidence in videos. Log-linear regression examines the influence of alternative communication channels on video creators in Biotechnology, using data from 81,302 papers (2018-2023). This reveals a positive association with news articles and Wikipedia pages, but a...
Recent advances in large language models (LLMs) allow agents to represent actions as executable code, offering greater expressivity than traditional tool-calling. However, real-world tasks often demand both strategic planning and detailed implementation. Using a single agent for both leads to context pollution from debugging traces...
Alerts are critical for detecting anomalies in large-scale cloud systems, ensuring reliability and user experience. However, current systems generate overwhelming volumes of alerts, degrading operational efficiency due to ineffective alert life-cycle management. This paper details the efforts of Company-X to optimize alert life-cycle...
The rapid expansion of Transformer-based large language models has dramatically increased the need for high-performance GPUs. As a result, there is growing demand for fast, accurate, and widely generalizable GPU performance models to support next-generation hardware selection and system-level exploration. However, current data-driven...
(First-order) transductions are a basic notion capturing graph modifications that can be described in first-order logic. In this work, we propose an efficient algorithmic method to approximately reverse the application of a transduction, assuming the source graph is sparse. Precisely, for any graph class $\mathcal{C}$ that has...
Large language models (LLMs) have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque. Mechanistic interpretability (i.e., the systematic study of how neural networks implement algorithms through their learned representations and computational structures) has...
Podcast script generation requires LLMs to synthesize structured, context-grounded dialogue from diverse inputs, yet systematic evaluation resources for this task remain limited. To bridge this gap, we introduce PodBench, a benchmark comprising 800 samples with inputs up to 21K tokens and complex multi-speaker instructions. We propose...
Parser-based log compression, which separates static templates from dynamic variables, is a promising approach to exploit the unique structure of log data. However, its performance on complex production logs is often unsatisfactory. This performance gap coincides with a known degradation in the accuracy of its core log parsing...
Bangla music is enrich in its own music cultures. Now a days music genre classification is very significant because of the exponential increase in available music, both in digital and physical formats. It is necessary to index them accordingly to facilitate improved retrieval. Automatically classifying Bangla music by genre is...
Graph Neural Networks (GNNs) are neural networks that aim to process graph data, capturing the relationships and interactions between nodes using the message-passing mechanism. GNN quantization has emerged as a promising approach for reducing model size and accelerating inference in resource-constrained environments. Compared to...
Structural approaches to myth and narrative are compelling in close reading but hard to compare across traditions, media, and scale. We propose a formal framework that renders Lévi-Straussian transformation as mathematics while remaining readable as narrative analysis. Variants, superhero continuities, and franchise arcs are modeled...
Multi-agent systems (MAS) composed of large language models often exhibit improved problem-solving performance despite operating on identical information. In this work, we provide a formal explanation for this phenomenon grounded in operator theory and constrained optimization. We model each agent as enforcing a distinct family of...
Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering. As these systems become more autonomous and are deployed at scale, understanding why an agent takes a particular action becomes increasingly important for accountability and governance....
Differential fuzzers detect bugs by executing identical inputs across distinct implementations of the same specification, such as JavaScript interpreters. Validating the outputs requires an oracle and for differential testing of JavaScript, these are constructed manually, making them expensive, time-consuming, and prone to false...
Decoding visual experiences from human brain activity remains a central challenge at the intersection of neuroscience, neuroimaging, and artificial intelligence. A critical obstacle is the inherent variability of cortical responses: neural activity elicited by the same visual stimulus differs across individuals and trials due to...
With increasing levels of robot autonomy, robots are increasingly being supervised by users with varying levels of robotics expertise. As the diversity of the user population increases, it is important to understand how users with different expertise levels approach the supervision task and how this impacts performance of the...
The economic warehouse lot scheduling problem is a foundational inventory-theory model, capturing computational challenges in dynamically coordinating replenishment decisions for multiple commodities subject to a shared capacity constraint. Even though this model has generated a vast body of literature over the last six decades, our...
In this paper, we propose a novel cross-domain channel estimation (CDCE) algorithm for orthogonal frequency division multiplexing (OFDM) systems, leveraging the unique characteristics of the delay-Doppler (DD) domain channel. Specifically, the proposed algorithm transforms the time-frequency (TF) domain pilot sequence of OFDM into the...
CLIP-based foreground-background (FG-BG) decomposition methods have demonstrated remarkable effectiveness in improving few-shot out-of-distribution (OOD) detection performance. However, existing approaches still suffer from several limitations. For background regions obtained from decomposition, existing methods adopt a uniform...
AI has revolutionised decision-making across various fields. Yet human judgement remains paramount for high-stakes decision-making. This has fueled explorations of collaborative decision-making between humans and AI systems, aiming to leverage the strengths of both. To explore this dynamic, researchers conduct empirical studies,...
Scientific fields are often mapped using citations and metadata, despite knowledge being transmitted primarily through content. We introduce an 'inside-out' approach that reconstructs field structure directly from text by representing each paper as a small set of interpretable knowledge components. Using a large language model to...
Traditional data masking techniques such as anonymization cannot achieve the expected privacy protection while ensuring data utility for privacy-preserving machine learning. Synthetic data plays an increasingly important role as it generates a large number of training samples and prevents information leakage in real data. The existing...
End-to-end automatic speech recognition (ASR) systems frequently misrecognize domain-specific phrases like named entities, which can cause catastrophic failures in downstream tasks. A new family of named entity correction methods based on large language models (LLMs) has recently emerged. However, these approaches have yet to fully...
Modern CI/CD pipelines integrating agent-generated code exhibit a structural failure in responsibility attribution. Decisions are executed through formally correct approval processes, yet no entity possesses both the authority to approve those decisions and the epistemic capacity to meaningfully understand their basis. We define...
Falls are the leading cause of injury related hospitalization and mortality among older adults. Consequently, mitigating age-related declines in gait stability and reducing fall risk during walking is a critical goal for assistive devices. Lower-limb exoskeletons have the potential to support users in maintaining stability during...