341

arXiv:2512.05948v2 Announce Type: replace
Abstract: Public-use microdata samples (PUMS) from the United States (US) Census Bureau on individuals have been available for decades. However, large increases in computing power and the greater availability of Big Data have dramatically increased the prob…
319

arXiv:2503.10043v2 Announce Type: replace
Abstract: Image super-resolution (SR) aims to recover low-resolution images to high-resolution images, where improving SR efficiency is a high-profile challenge. However, commonly used units in SR, like convolutions and window-based Transformers, have limit…
334

In late September, a Spanish military plane carrying the country’s defense minister to a base in Lithuania was reportedly the subject of a kind of attack—not by a rocket or anti-aircraft rounds, but by radio transmissions that jammed its GPS system.  The flight landed safely, but it was one of thous…
321

arXiv:2510.08808v4 Announce Type: replace
Abstract: Graphs provide a universal framework for representing complex relational systems, and inferring their structural properties is a core challenge in graph analysis and reasoning. While large language models have recently demonstrated emerging abilit…
219

Chile has just elected its first far-right leader, Jose Antonio Kast, since the fall of the dictator Augusto Pinochet in 1990. The arch conservative politician was elected on an anti-crime and anti-immigration platform, which won over 60% of voters. But "Kast has also been leading the fight against …
330

arXiv:2512.12590v1 Announce Type: new
Abstract: Wire harness inspection process remains a labor-intensive process prone to errors in the modern Electronics Manufacturing Services (EMS) industry. This paper introduces a semiautomated machine vision system capable of verifying correct wire positionin…
321

arXiv:2506.23046v3 Announce Type: replace
Abstract: Humans continuously infer the states, goals, and behaviors of others by perceiving their surroundings in dynamic, real-world social interactions. However, most Theory of Mind (ToM) benchmarks only evaluate static, text-based scenarios, which have …
318

Liverpool great understood to be recovering wellClub thank hospital for giving ‘the best care possible’Ian Rush has been released from hospital having spent two days in intensive care last week with flu.The former Liverpool and Wales striker was admitted to the Countess of Chester hospital with brea…
208

arXiv:2512.12183v1 Announce Type: new
Abstract: Recent advances have introduced diffusion models for probabilistic streamflow forecasting, demonstrating strong early flood-warning skill. However, current implementations rely on recurrent Long Short-Term Memory (LSTM) backbones and single-step train…
238

arXiv:2408.06069v2 Announce Type: replace
Abstract: Deep Gaussian process models typically employ discrete hierarchies, but recent advancements in differential Gaussian processes (DiffGPs) have extended these models to infinite depths. However, existing DiffGP approaches often overlook the uncertai…
231

arXiv:2512.12870v1 Announce Type: new
Abstract: Active Learning (AL) has garnered significant interest across various application domains where labeling training data is costly. AL provides a framework that helps practitioners query informative samples for annotation by oracles (labelers). However,…
211

arXiv:2512.13510v1 Announce Type: new
Abstract: Large language models with reasoning capabilities have demonstrated impressive performance across a wide range of domains. In clinical applications, a transparent, step-by-step reasoning process provides physicians with strong evidence to support deci…
222

The chair of the House of Lords Environment and Climate Change Committee has written to the environment secretary expressing “deep disappointment” at the government’s response to its waste-crime inquiry.
The post Lords write to environment secretary over “complacent” response to waste crime inquiry …
223

Dashcam footage shows the moment Boris Gurman tackles shooter Sajid Akram and wrestles a gun from himDramatic footage has emerged of two victims who tried to stop a gunman during the early stages of the Bondi beach terror attack on Sunday.The couple have been identified as Boris Gurman, 69, and Sofi…
231

arXiv:2512.12900v1 Announce Type: new
Abstract: We present a \emph{deterministic exact algorithm} for the \emph{minimum $k$-cut problem} on simple graphs.
Our approach combines the \emph{principal sequence of partitions (PSP)}, derived canonically from ideal loads, with a single level of \emph{Ka…
229

arXiv:2512.12391v1 Announce Type: new
Abstract: $\renewcommand{\Re}{\mathbb{R}}$We present an efficient $O (n + 1/\varepsilon^{4.5})$-time algorithm for computing a $(1+\varepsilon$)-approximation of the minimum-volume bounding box of $n$ points in $\Re^3$. We also present a simpler algorithm (for …
139

arXiv:2512.13515v1 Announce Type: new
Abstract: The study presents the outcomes of research and experimental validation in the domain of automated codebase migration, with a focus on addressing challenges in transitioning SQL-based systems. The proposed method for migration essentially appears as a…
221

arXiv:2512.12132v1 Announce Type: new
Abstract: This article establishes a comprehensive theoretical framework demonstrating that SiLU (Sigmoid Linear Unit) activation networks achieve exponential approximation rates for smooth functions with explicit and improved complexity control compared to cla…
111

arXiv:2512.12443v1 Announce Type: new
Abstract: AI model documentation is fragmented across platforms and inconsistent in structure, preventing policymakers, auditors, and users from reliably assessing safety claims, data provenance, and version-level changes. We analyzed documentation from five fr…
231

arXiv:2512.13281v1 Announce Type: new
Abstract: Recent advances in video generation have produced vivid content that are often indistinguishable from real videos, making AI-generated video detection an emerging societal challenge. Prior AIGC detection benchmarks mostly evaluate video without audio,…
212

arXiv:2512.12751v1 Announce Type: new
Abstract: Physics-aware driving world model is essential for drive planning, out-of-distribution data synthesis, and closed-loop evaluation. However, existing methods often rely on a single diffusion model to directly map driving actions to videos, which makes …
112

Hogshaw, Derbyshire: They’re in our paintings, in our folklore. A little opportunistic planting and I’ve got them in my gardenAs I cleared our garden of dead vegetation, including many old teasels, I realised that the latter were still shedding seeds and luring goldfinches to them. Not wishing to de…
208

arXiv:2512.11858v1 Announce Type: new
Abstract: Diffusion-based samplers -- Score Based Diffusions, Bridge Diffusions and Path Integral Diffusions -- match a target at terminal time, but the real leverage comes from choosing the schedule that governs the intermediate-time dynamics. We develop a pat…
212

Horizons Middle East & Africa is your daily spotlight on one of the world's fastest-growing regions. Live from Dubai, we bring you the latest global markets and analysis, plus news-making interviews, with a special focus on MEA. All that and more, as you head to the office in the Gulf, pause for lun…
222

arXiv:2512.12131v1 Announce Type: new
Abstract: The scale of transformer model pre-training is constrained by the increasing computation and communication cost. Low-rank bottleneck architectures offer a promising solution to significantly reduce the training time and memory footprint with minimum i…
210

Once prized fighters under the Tsars, Russia’s Cossack population was ostracised by authorities during the Soviet era. Under President Vladimir Putin, they have reintegrated into Russian society, acting as a supplementary police force and restoring their military status on the front lines in Ukraine…
110

When you next bite into a chicken sandwich, consider this: 2,400 of these birds are being slaughtered somewhere in the world every second. From street stalls in Mumbai to supermarkets in Beijing, chicken has become the world's most consumed meat. In 2023 alone, humans slaughtered an astonishing 76 b…
109

The best we can hope for is that Paul does not get seriously hurt. Joshua, Netflix and the sport itself should know betterPrecisely 85 years ago, one of the most fearsome heavyweight boxers in history stunk out the joint. Joe Louis was in the midst of his “Bum of the Month club”: a staggering run of…
109

High court rules whole cooked cool-down chickens should be subject to standard 20% tax rate for hot foodBusiness live – latest updatesThe UK supermarket chain Morrisons faces a £17m tax bill after losing a lengthy court battle against HMRC over the charging of value added tax (VAT) on rotisserie chi…
122

arXiv:2507.01131v4 Announce Type: replace
Abstract: $\rm{SO}(3)$-equivariant networks are the dominant models for machine learning interatomic potentials (MLIPs). The key operation of such networks is the Clebsch-Gordan (CG) tensor product, which is computationally expensive. To accelerate the comp…
121

arXiv:2509.16339v4 Announce Type: replace
Abstract: We investigate imbalanced regression with tabular data that have an imbalance ratio larger than 1,000 ("highly imbalanced"). Accurately estimating the target values of rare instances is important in applications such as forecasting the intensity o…
111

arXiv:2509.24561v2 Announce Type: replace
Abstract: Symmetric kernel matrices are a well-researched topic in the literature of kernel based approximation. In particular stability properties in terms of lower bounds on the smallest eigenvalue of such symmetric kernel matrices are thoroughly investig…
111

arXiv:2512.12731v1 Announce Type: new
Abstract: This paper studies a machine learning regression problem as a multivariate approximation problem using the framework of the theory of random functions. An ab initio derivation of a regression method is proposed, starting from postulates of indifferenc…
108

arXiv:2512.12554v1 Announce Type: new
Abstract: Logic optimization constitutes a critical phase within the Electronic Design Automation (EDA) flow, essential for achieving desired circuit power, performance, and area (PPA) targets. These logic circuits are typically represented as Directed Acyclic …
123

arXiv:2512.11900v1 Announce Type: new
Abstract: We study data-driven identification of interpretable hybrid robot dynamics, where an analytical rigid-body dynamics model is complemented by a learned residual torque term. Using symbolic regression and sparse identification of nonlinear dynamics (SIN…
110

arXiv:2510.14945v2 Announce Type: replace
Abstract: We present 3DScenePrompt, a framework that generates the next video chunk from arbitrary-length input while enabling precise camera control and preserving scene consistency. Unlike methods conditioned on a single image or a short clip, we employ d…
111

arXiv:2512.11835v1 Announce Type: new
Abstract: Large language models (LLMs) are often deployed as powerful yet opaque systems, leaving open how their internal memory and "self-like" behavior should be governed in a principled and auditable way. The Artificial Age Score (AAS) was previously introdu…
110

arXiv:2512.12088v1 Announce Type: new
Abstract: In a recent work, we proposed Reliable Policy Iteration (RPI), that restores policy iteration's monotonicity-of-value-estimates property to the function approximation setting. Here, we assess the robustness of RPI's empirical performance on two classi…
109

arXiv:2512.12779v1 Announce Type: new
Abstract: Real-world datasets frequently exhibit evolving data distributions, reflecting temporal variations and underlying shifts. Overlooking this phenomenon, known as concept drift, can substantially degrade the predictive performance of the model. Furthermo…
111

arXiv:2512.13039v1 Announce Type: new
Abstract: Concept erasure, which fine-tunes diffusion models to remove undesired or harmful visual concepts, has become a mainstream approach to mitigating unsafe or illegal image generation in text-to-image models.However, existing removal methods typically ad…
109

arXiv:2512.12536v1 Announce Type: new
Abstract: Large Language Models (LLMs) are increasingly being studied for Software Vulnerability Detection (SVD) and Repair (SVR). Individual LLMs have demonstrated code understanding abilities, but they frequently struggle when identifying complex vulnerabilit…