arXiv preprints from January 1, 2026 through July 20, 2026 — 17:47:45 EST
Recent years have seen substantial progress in neural generation of text, images, and audio, supported by mature training pipelines and large-scale optimization. For graphs, however, comparable progress has been more limited. We attribute this gap to graph-specific optimization and representation challenges that undermine the...
Bayesian model comparison implements Occam's razor through its sensitivity to the prior. However, prior-dependence makes it important to assess the influence of plausible alternative priors. Such prior sensitivity analyses for the Bayesian evidence are expensive, either requiring repeated, costly model re-fits or specialised sampling...
In this paper, we study the vehicle routing problem with a finite time horizon. In this routing problem, the objective is to maximize the number of customer requests served within a finite time horizon. We present a novel routing network embedding module which creates local node embedding vectors and a context-aware global graph...
The ubiquity of Large Language Models (LLMs) is driving a paradigm shift where user convenience supersedes computational efficiency. This article defines the "Plausibility Trap": a phenomenon where individuals with access to Artificial Intelligence (AI) models deploy expensive probabilistic engines for simple deterministic tasks-such...
Multimodal large language models have demonstrated comparable performance to that of radiology trainees on multiple-choice board-style exams. However, to develop clinically useful multimodal LLM tools, high-quality benchmarks curated by domain experts are essential. To curate released and holdout datasets of 100 chest radiographic...
We study determinantal varieties from conditional independence models with hidden variables, focusing on their irreducible decompositions, dimensions, degrees, and Gröbner bases. Each variety encodes a collection of matroids, whose flats capture algebraic dependencies among variables. Using this approach, we provide a systematic...
Deploying federated learning across heterogeneous IoT device fleets requires tailored neural network architectures for each device class, yet existing Federated Neural Architecture Search (FedNAS) methods suffer from unguided supernet training and prohibitively costly post-training search pipelines that demand over 20 GPU-hours per...
This chapter focuses on active sensing using sparse arrays. In active sensing applications, such as radar, sonar, wireless communications, and medical ultrasound, a collection of sensors probes the environment by emitting self-generated energy. A key benefit of such active multi-sensor arrays is their ability to focus and steer energy...
In a recent publication [R. C. Tautz and I. Lerche, Res. Astron. Astrophys. 16, 162 (2016); arXiv:1606.08272], the authors present a derivation of the Green's function for the three-dimensional telegraph equation (also known as the heat wave equation, or relativistic heat conduction equation). We demonstrate that the closed-form...
Graph Foundation Models (GFMs) have emerged as a frontier in graph learning, which are expected to deliver transferable representations across diverse tasks. However, GFMs remain constrained by in-memory bottlenecks: they attempt to encode knowledge into model parameters, which limits semantic capacity, introduces heavy lossy...
Promptable segmentation models such as SAM have established a powerful paradigm, enabling strong generalization to unseen objects and domains with minimal user input, including points, bounding boxes, and text prompts. Among these, bounding boxes stand out as particularly effective, often outperforming points while significantly...
Popularity bias is a pervasive challenge in recommender systems, where a few popular items dominate attention while the majority of less popular items remain underexposed. This imbalance can reduce recommendation quality and lead to unfair item exposure. Although existing mitigation methods address this issue to some extent, they...
Cooperative effects in oscillator networks are often associated with enhanced stability of phase-locked solutions, which increases with system size. We show that the stabilization of persistent currents in annular atomic superfluids with periodic barriers is a concrete manifestation of this phenomenon. Under the simplifying assumption...
LLMs have advanced tool-using agents for real-world applications, yet they often lead to unexpected behaviors or results. Beyond obvious failures, the subtle issue of "intent deviation" severely hinders reliable evaluation and performance improvement. Existing post-training methods generally leverage either real system samples or...
Polycystic Ovary Syndrome (PCOS) is the most familiar endocrine illness in women of reproductive age. Many Bangladeshi women suffer from PCOS disease in their older age. The aim of our research is to identify effective vision-based medical image analysis techniques and evaluate hybrid models for the accurate detection of PCOS. We...
Whisper has become the de-facto encoder for extracting general-purpose audio features in large audio-language models, where a 30-second clip is typically represented by 1500 frame features projected into an LLM. In contrast, audio-text embedding models like CLAP-based models have largely relied on alternative audio encoders (e.g.,...
We frame the Painlevè mechanical system, which has been extensively studied because of the paradox it generates, within the class of Regular Geometric Impulsive Mechanical Systems (RGIMS), by modeling it as a mechanical system subject to a rough unilateral positional constraint $\cal{S}$, where friction is represented by an...
The BESIII Collaboration has collected large data samples from $e^+e^-$ collisions at center-of-mass energies ranging from 1.84 to 4.95 GeV, which include the world's largest charmonium sample, consisting of 10 billion $J/ψ$ and 3 billion $ψ(3686)$ events. These high-statistics datasets enable BESIII to carry out a wide range of...
Hateful videos pose serious risks by amplifying discrimination, inciting violence, and undermining online safety. Existing training-based hateful video detection methods are constrained by limited training data and lack of interpretability, while directly prompting large vision-language models often struggle to deliver reliable hate...
Generative Agent-Based Modeling (GABM) leverages Large Language Models to create autonomous agents that simulate human behavior in social media environments, demonstrating potential for modeling information propagation, influence processes, and network phenomena. While existing frameworks characterize agents through demographic...
Wireless imaging has become a vital function in future integrated sensing and communication (ISAC) systems. However, traditional model-based and data-driven deep learning imaging methods face challenges related to multipath extraction, dataset acquisition, and multi-scenario adaptation. To overcome these limitations, this study...
We expose a critical limitation in current approaches to machine unlearning in language models: despite the apparent success of unlearning algorithms, information about the forgotten data remains linearly decodable from internal representations. To systematically assess this discrepancy, we introduce an interpretable,...
In an entanglement summoning task, a set of distributed, co-operating parties attempt to fulfill requests to prepare entanglement between distant locations. The parties share limited communication resources: timing constraints may require the entangled state be prepared before some pairs of distant parties can communicate, and a...
Garment simulation is fundamental to various applications in computer vision and graphics, from virtual try-on to digital human modelling. However, conventional physics-based methods remain computationally expensive, hindering their application in time-sensitive scenarios. While graph neural networks (GNNs) offer promising...
Interoperable data and intelligence flows among allied partners and operational end-users remain essential to NATO's collective defense across both conventional and hybrid threat environments. Foreign Information Manipulation and Interference (FIMI) increasingly spans multiple societal domains and information ecosystems, complicating...