arXiv preprints from January 1, 2026 through September 30, 2026 — 13:08:15 EST
Vision Transformers (ViTs) have gained rapid adoption in computational pathology for their ability to model long-range dependencies through self-attention, addressing the limitations of convolutional neural networks that excel at local pattern capture but struggle with global contextual reasoning. Recent pathology-specific foundation...
Capture-the-Flag (CTF) competitions play a central role in modern cybersecurity as a platform for training practitioners and evaluating offensive and defensive techniques derived from real-world vulnerabilities. Despite recent advances in large language models (LLMs), existing LLM-based agents remain ineffective on high-difficulty...
This paper investigates two fundamental descriptors of data, i.e., density distribution versus mass distribution, in the context of clustering. Density distribution has been the de facto descriptor of data distribution since the introduction of statistics. We show that density distribution has its fundamental limitation --...
In the noisy intermediate-scale quantum (NISQ) era, distributed quantum computation has garnered considerable interest, as it overcomes the physical limitations of single-device architectures and enables scalable quantum information processing. In this study, we focus on the challenge of achieving exact amplitude amplification for...
Robo-advisors (RAs) are automated portfolio management systems that complement traditional financial advisors by offering lower fees and smaller initial investment requirements. While most existing RAs rely on static, one-period allocation methods, we propose a dynamic, multi-period asset-allocation framework that leverages Model...
Distributional representations of data collected using digital health technologies have been shown to outperform scalar summaries for clinical prediction, with carefully quantified tail-behavior often driving the gains. Motivated by these findings, we propose a unified generalized odds (GO) framework that represents subject-specific...
Multi-turn GUI agents enable complex task completion through sequential decision-making, but suffer from severe context inflation as interaction history accumulates. Existing strategies either sacrifice long-term context via truncation or compromise spatial structure through token pruning. In this paper, we propose Coordinate...
Group Recommender Systems (GRS) play an essential role in supporting collective decision-making among users with diverse and potentially conflicting preferences. However, achieving stable intra-group consensus becomes particularly challenging when only sparse userID-itemID-rating data are available and no demographic, contextual, or...
Chip-firing on a directed graph is a game in which chips, a discrete commodity, are placed on the vertices of the graph and are transferred between vertices. In this paper, we study a chip-firing game on the Hasse diagram of the lattice of nonnegative integer points on the plane, where we start with $2^n$ chips at the origin. When we...
Artificial Intelligence (AI) infrastructure faces two compounding crises. Compute payload - the unsustainable energy and capital costs of training and inference - threatens to outpace grid capacity and concentrate capability among a handful of organizations. Data chaos - the 80% of project effort consumed by preparation, conversion,...
Phonons, quantized vibrations of the atomic lattice, are fundamental to understanding thermal transport, structural stability, and phase behavior in crystalline solids. Despite advances in computational materials science, most predictions of vibrational properties in large materials databases rely on the harmonic approximation and...
Posterior tempering reduces the influence of the likelihood in the calculation of the posterior by raising the likelihood to a fractional power $α$. The resulting power posterior - also known as an $α$-posterior or fractional posterior - has been shown to exhibit appealing properties, including robustness to model misspecification and...
Single-domain generalized deep metric learning (SDG-DML) faces the dual challenge of both category and domain shifts during testing, limiting real-world applications. Therefore, aiming to learn better generalization ability on both unseen categories and domains is a realistic goal for the SDG-DML task. To deliver the aspiration,...
Tool-augmented large language models (LLMs) have powered many applications. However, they are likely to suffer from knowledge conflict. In this paper, we propose a new type of knowledge conflict -- Tool-Memory Conflict (TMC), where the internal parametric knowledge contradicts with the external tool knowledge for tool-augmented LLMs....
Current patent claim generation systems face three fundamental limitations: poor cross-jurisdictional generalization, inadequate semantic relationship modeling between claims and prior art, and unreliable quality assessment. We introduce a novel three-stage framework that addresses these challenges through relationship-aware...
Fine-grained labor market analysis increasingly relies on mapping unstructured job advertisements to standardized skill taxonomies such as ESCO. This mapping is naturally formulated as an Extreme Multi-Label Classification (XMLC) problem, but supervised solutions are constrained by the scarcity and cost of large-scale,...
This paper addresses the limitations of current vision-based rail defect detection methods, including high computational complexity, excessive parameter counts, and suboptimal accuracy. We propose a Lightweight Pyramid Cross-Attention Network (LPCANet) that leverages RGB-D data for efficient and accurate defect identification. The...
Generative AI systems increasingly enable the production of highly realistic synthetic media. Civitai, a popular community-driven platform for AI-generated content, operates a monetized feature called Bounties, which allows users to commission the generation of content in exchange for payment. To examine how this mechanism is used and...
Real-world License Plate Recognition (LPR) faces significant challenges from severe degradations such as motion blur, low resolution, and complex illumination. The prevailing "restoration-then-recognition" two-stage paradigm suffers from a fundamental flaw: the pixel-level optimization objectives of image restoration models are...
We present SASHMAG (Saturated Absorption Spectroscopy High-field MAGnetometer), an atomic sensor designed for precision magnetic-field measurements in the intermediate-to-high field regime ($>0.2\,\text{T}$) using Rubidium-87 ($^{87}Rb$). The sensor operates in the hyperfine Paschen-Back regime, where the hyperfine and Zeeman...
Large language model (LLM)-based agents are increasingly deployed in applications, such as trip-planning agents and web-use agents, to perform complex planning and execution tasks. Prior work has shown that LLM-based agents are vulnerable to context confusion, where external adversarial content incorporated into the agent's reasoning...
The GEneral Matrix Multiplication (GEMM) is one of the essential algorithms in scientific computing. Single-thread GEMM implementations are well-optimised with techniques like blocking and autotuning. However, due to the complexity of modern multi-core shared memory systems, it is challenging to determine the number of threads that...
Memory plays a foundational role in augmenting the reasoning, adaptability, and contextual fidelity of modern Large Language Models and Multi-Modal LLMs. As these models transition from static predictors to interactive systems capable of continual learning and personalized inference, the incorporation of memory mechanisms has emerged...
The rapid development of generative AI has brought value- and ethics-related risks to the forefront, making value safety a critical concern while a unified consensus remains lacking. In this work, we propose an internationally inclusive and resilient unified value framework, the GenAI Value Safety Scale (GVS-Scale): Grounded in a...
Vision-Language Navigation (VLN) aims to enable agents to navigate to a target location based on language instructions. Traditional VLN often follows a close-set assumption, i.e., training and test data share the same style of the input images and instructions. However, the real world is open and filled with various unseen...