Comparative Analysis of 3D Convolutional and 2.5D Slice-Conditioned U-Net Architectures for MRI Super-Resolution via Elucidated Diffusion Models

arXiv:2603.14667v1 Announce Type: cross Abstract: Magnetic resonance imaging (MRI) super-resolution (SR) methods that computationally enhance low-resolution acquisitions to approximate high-resolution quality offer a compelling alternative to expensive high-field scanners. In this work we investigate an elucidated diffusion model (EDM) framework for brain MRI SR and compare two U-Net backbone architectures: (i) a full 3D convolutional […]

Universe Routing: Why Self-Evolving Agents Need Epistemic Control

arXiv:2603.14799v1 Announce Type: cross Abstract: A critical failure mode of current lifelong agents is not lack of knowledge, but the inability to decide how to reason. When an agent encounters “Is this coin fair?” it must recognize whether to invoke frequentist hypothesis testing or Bayesian posterior inference – frameworks that are epistemologically incompatible. Mixing them […]

A Dual-Path Generative Framework for Zero-Day Fraud Detection in Banking Systems

arXiv:2603.13237v1 Announce Type: new Abstract: High-frequency banking environments face a critical trade-off between low-latency fraud detection and the regulatory explainability demanded by GDPR. Traditional rule-based and discriminative models struggle with “zero-day” attacks due to extreme class imbalance and the lack of historical precedents. This paper proposes a Dual-Path Generative Framework that decouples real-time anomaly detection […]

AI-Driven Predictive Maintenance with Real-Time Contextual Data Fusion for Connected Vehicles: A Multi-Dataset Evaluation

arXiv:2603.13343v1 Announce Type: cross Abstract: Most vehicle predictive maintenance systems rely exclusively on internal diagnostic signals and are validated on deterministic synthetic data, limiting the credibility of reported metrics. This paper presents a simulation-validated proof-of-concept framework for V2X-augmented predictive maintenance, integrating on-board sensor streams with external contextual signals — road quality, weather, traffic density, and […]

Nudging Hidden States: Training-Free Model Steering for Chain-of-Thought Reasoning in Large Audio-Language Models

arXiv:2603.14636v1 Announce Type: cross Abstract: Chain-of-thought (CoT) prompting has been extended to large audio-language models (LALMs) to elicit reasoning, yet enhancing its effectiveness without training remains challenging. We study inference-time model steering as a training-free approach to improve LALM reasoning. We introduce three strategies using diverse information sources and evaluate them across four LALMs and […]

Aura: Universal Multi-dimensional Exogenous Integration for Aviation Time Series

arXiv:2603.05092v2 Announce Type: replace-cross Abstract: Time series forecasting has witnessed an increasing demand across diverse industrial applications, where accurate predictions are pivotal for informed decision-making. Beyond numerical time series data, reliable forecasting in practical scenarios requires integrating diverse exogenous factors. Such exogenous information is often multi-dimensional or even multimodal, introducing heterogeneous interactions that unimodal time […]

WaveComm: Lightweight Communication for Collaborative Perception via Wavelet Feature Distillation

arXiv:2603.13365v1 Announce Type: cross Abstract: In multi-agent collaborative sensing systems, substantial communication overhead from information exchange significantly limits scalability and real-time performance, especially in bandwidth-constrained environments. This often results in degraded performance and reduced reliability. To address this challenge, we propose WaveComm, a wavelet-based communication framework that drastically reduces transmission loads while preserving sensing performance […]

Malicious Agent Skills in the Wild: A Large-Scale Security Empirical Study

arXiv:2602.06547v2 Announce Type: replace-cross Abstract: Third-party agent skills extend LLM-based agents with instruction files and executable code that run on users’ machines. Skills execute with user privileges and are distributed through community registries with minimal vetting, but no ground-truth dataset exists to characterize the resulting threats. We construct the first labeled dataset of malicious agent […]

Do Mixed-Vendor Multi-Agent LLMs Improve Clinical Diagnosis?

arXiv:2603.04421v2 Announce Type: replace-cross Abstract: Multi-agent large language model (LLM) systems have emerged as a promising approach for clinical diagnosis, leveraging collaboration among agents to refine medical reasoning. However, most existing frameworks rely on single-vendor teams (e.g., multiple agents from the same model family), which risk correlated failure modes that reinforce shared biases rather than […]

Hide and Seek: Investigating Redundancy in Earth Observation Imagery

arXiv:2603.13524v1 Announce Type: cross Abstract: The growing availability of Earth Observation (EO) data and recent advances in Computer Vision have driven rapid progress in machine learning for EO, producing domain-specific models at ever-increasing scales. Yet this progress risks overlooking fundamental properties of EO data that distinguish it from other domains. We argue that EO data […]

Beyond Linearity in Attention Projections: The Case for Nonlinear Queries

arXiv:2603.13381v1 Announce Type: cross Abstract: Recent algebraic analysis shows that in decoder-only and encoder-only transformers, the Query projection $W_Q$ may be set to identity without noticeable performance deterioration. This is possible because attention depends on $X$ only through the products $XW_Q, XW_K, XW_V$, allowing basis transformations to be absorbed by adjacent layers and propagated through […]

Subscribe for Updates

Copyright 2025 dijee Intelligence Ltd.   dijee Intelligence Ltd. is a private limited company registered in England and Wales at Media House, Sopers Road, Cuffley, Hertfordshire, EN6 4RY, UK registration number 16808844