digitado

arXiv:2604.06256v1 Announce Type: new Abstract: Training dynamics during grokking concentrate along a small number of dominant update directions — the spectral edge — which reliably distinguishes grokking from non-grokking regimes. We show that standard mechanistic interpretability tools (head attribution, activation probing, sparse autoencoders) fail to capture these directions: their structure is not localized in parameter or feature space. Instead, each direction induces a structured function over the input domain, revealing low-dimensional functional modes invisible to representation-level analysis. For […]

Ver mais

arXiv:2604.06254v1 Announce Type: new Abstract: With the rapid growth of interconnected devices in Industrial and Medical Internet of Things (IIoT and MIoT) ecosystems, ensuring timely and accurate detection of cyber threats has become a critical challenge. This study presents an advanced intrusion detection framework based on a hybrid Squeeze-and-Excitation Attention Vision Transformer-Bidirectional Long Short-Term Memory (SE ViT-BiLSTM) architecture. In this design, the traditional multi-head attention mechanism of the Vision Transformer is replaced with Squeeze-and-Excitation attention, and integrated with […]

Ver mais

arXiv:2604.06253v1 Announce Type: new Abstract: Cross-lingual code generation is critical in enterprise environments where multiple programming languages coexist. However, fine-tuning large language models (LLMs) individually for each language is computationally prohibitive. This paper investigates whether parameter-efficient fine-tuning methods and optimizer enhancements can improve cross-lingual transfer from Python to languages like Java. We fine-tune the Code Llama 7B model using low-rank adaptation (LoRA) to optimize a small subset of parameters and compare Adam and Sophia optimizers, while exploring a […]

Ver mais

arXiv:2604.06252v1 Announce Type: new Abstract: The exponential growth of Common Vulnerabilities and Exposures (CVE) disclosures poses significant challenges for enterprise security management, necessitating automated and quantitative risk assessment methodologies. Existing vulnerability analysis approaches suffer from three critical limitations: (1) lack of systematic severity quantification models that integrate heterogeneous attack attributes, (2) insufficient exploration of latent correlations among risk factors, and (3) absence of cumulative risk distribution analysis for prioritized remediation. To address these challenges, we propose MVRAF (Multi-dimensional […]

Ver mais

arXiv:2604.06251v1 Announce Type: new Abstract: This article presents the results of a data science study conducted at a container terminal, aimed at reducing unproductive container moves through the prediction of service requirements and container dwell times. We develop and evaluate machine learning models that leverage historical operational data to anticipate which containers will require pre-clearance handling services prior to cargo release and to estimate how long they are expected to remain in the terminal. As part of the […]

Ver mais

arXiv:2604.06250v1 Announce Type: new Abstract: When asked to describe a molecular diagram, a Vision-Language Model correctly identifies “a benzene ring with an -OH group.” When asked to reason about the same image, it answers incorrectly. The model can see but it cannot think about what it sees. We term this the perception-integration gap: a failure where visual information is successfully extracted but lost during downstream reasoning, invisible to single-configuration benchmarks that conflate perception with integration under one accuracy […]

Ver mais

arXiv:2604.06247v1 Announce Type: new Abstract: Large Language Models (LLMs) and Vision-Language Models (VLMs) remain highly vulnerable to textual and visual jailbreaks, as well as prompt injections (arXiv:2307.15043, Greshake et al., 2023, arXiv:2306.13213). Existing defenses often degrade performance through complex input transformations or treat multimodal threats as isolated problems (arXiv:2309.00614, arXiv:2310.03684, Zhang et al., 2025). To address the critical gap for a unified, modal-agnostic defense that mitigates both textual and visual threats simultaneously without degrading performance or requiring architectural […]

Ver mais

arXiv:2604.06246v1 Announce Type: new Abstract: Iterative reconstruction technique’s ability to reduce radiation exposure by using fewer projections has attracted significant attention. However, these methods typically require a precise tuning of several hyperparameters, which can have a major impact on reconstruction quality. Manually setting these parameters is time-consuming and increases the workload for human operators. In this paper, we introduce a novel fully automatic parameter optimization framework that can be applied to a wide range of Cone-beam computed tomography […]

Ver mais

arXiv:2604.06245v1 Announce Type: new Abstract: Impact craters are a cornerstone of planetary surface analysis. However, while most deep learning pipelines treat craters solely as a detection problem, critical scientific workflows such as catalog deduplication, cross-observation matching, and morphological analog discovery are inherently retrieval tasks. To address this, we formulate crater analysis as an instance-level image retrieval problem and introduce CraterBench-R, a curated benchmark featuring about 25,000 crater identities with multi-scale gallery views and manually verified queries spanning diverse […]

Ver mais

arXiv:2604.06241v1 Announce Type: new Abstract: AI IDEs and coding agents compress discovery, fetch, workspace open, installation, and execution into one low-observability loop. Existing defenses such as provenance frameworks, package and repository firewalls, runtime protection, and tool-approval prompts each cover part of that path, but they often leave the final consumer-side execution decision implicit. ZitPit is a 100% open-source Rust system that argues for a stricter boundary: first-seen external artifacts should become durable policy events before they gain execution […]

Ver mais