arXiv:2510.20372v3 Announce Type: replace Abstract: Small influential data subsets can dramatically impact model conclusions, with a few data points overturning key findings. While recent work identifies these most influential sets, there is no formal way to tell when maximum influence is excessive rather than expected under natural random sampling variation. We address this gap by developing a principled framework for most influential sets. Focusing on linear least-squares, we derive a convenient exact influence formula and identify the extreme […]

Ver mais

In the fast-evolving hospitality landscape of 2026, a new specialist is quietly driving outsized results: the Sales IT Data Analyst. This hybrid professional bridges sales strategy, robust IT infrastructure, and advanced data analytics to optimize revenue streams across hotels, resorts, restaurants, and event venues. Unlike traditional revenue managers or general data analysts, these experts specialize in integrating real-time sales data flows with enterprise IT systems such as property management systems (PMS), CRM platforms, and point-of-sale (POS) tools to […]

Ver mais

arXiv:2603.10012v1 Announce Type: new Abstract: Military Large Language Models (LLMs) must provide accurate information to the warfighter in time-critical and dangerous situations. However, today’s LLMs are imbued with safety behaviors that cause the LLM to refuse many legitimate queries in the military domain, particularly those related to violence, terrorism, or military technology. Our gold benchmark for assessing refusal rates, which was developed by veterans of the US Army and special forces, is to our knowledge the first dataset […]

Ver mais

arXiv:2602.11220v1 Announce Type: new Abstract: Large language models (LLMs) have made rapid progress, yet adapting them to downstream scenarios still commonly relies on supervised fine-tuning (SFT). When downstream data exhibit a substantial distribution shift from the model’s prior training distribution, SFT can induce catastrophic forgetting. To narrow this gap, data rewriting has been proposed as a data-centric approach that rewrites downstream training data prior to SFT. However, existing methods typically sample rewrites from a prompt-induced conditional distribution, so […]

Ver mais

arXiv:2604.07353v1 Announce Type: new Abstract: Jean-Raymond Abrial is one of the central figures in the development of formal methods for software and systems engineering. Over a career spanning more than five decades, he has played a decisive role in the creation of the Z specification notation, the B-Method, and Event-B, and in demonstrating their applicability to large-scale industrial systems. This paper presents a scholarly biographical account of Abrial’s life and work, tracing the evolution of his ideas from […]

Ver mais

arXiv:2607.05735v1 Announce Type: new Abstract: Infinite-width limits are a standard way to reason about neural networks, but it is not automatic that the limiting learner has the same complexity-theoretic inductive bias as large finite networks. We study this question for Bayesian neural networks at the mean-field, or critical feature-learning, scaling. The central quantity is the emph{reduced entropy} [ s_infty(y,varepsilon)=limsup_N -frac{1}{N}log pi_N^0(Lle varepsilon), ] the intensive prior cost of representing a target function $y$ to population mean-squared error $varepsilon$. […]

Ver mais

arXiv:2603.24744v1 Announce Type: new Abstract: Weather data, comprising multiple variables, poses significant challenges due to its high dimensionality and multimodal nature. Creating low-dimensional embeddings requires compressing this data into a compact, shared latent space. This compression is required to improve the efficiency and performance of downstream tasks, such as forecasting or extreme-weather detection. Self-supervised learning, particularly contrastive learning, offers a way to generate low-dimensional, robust embeddings from unlabelled data, enabling downstream tasks when labelled data is scarce. Despite […]

Ver mais

arXiv:2604.02381v1 Announce Type: new Abstract: The rapid development of agentic artificial intelligence (AI) is driving future wireless networks to evolve from passive data pipes into intelligent collaborative ecosystems under the emerging paradigm of integrated learning and communication (ILAC). However, realizing efficient agentic collaboration faces challenges not only in handling semantic redundancy but also in the lack of an integrated mechanism for communication, computation, and control. To address this, we propose a wireless agent network (WAN) framework that orchestrates […]

Ver mais