arXiv:2604.25924v1 Announce Type: new Abstract: Large Language Models have been increasingly employed in the creation of Virtual Assistants due to their ability to generate human-like text and handle complex inquiries. While these models hold great promise, challenges such as hallucinations, missing information, and the difficulty of providing accurate and context-specific responses persist, particularly when applied to highly specialized content domains. In this paper, we focus on addressing these challenges by developing a virtual assistant designed to support students […]

Ver mais

arXiv:2602.22277v1 Announce Type: new Abstract: AI-native architectures are vital for 6G wireless communications. The black-box nature and high complexity of deep learning models employed in critical applications, such as channel estimation, limit their practical deployment. While perturbation-based XAI solutions offer input filtering, they often neglect internal structural optimization. We propose X-REFINE, an XAI-based framework for joint input-filtering and architecture fine-tuning. By utilizing a decomposition-based, sign-stabilized LRP epsilon rule, X-REFINE backpropagates predictions to derive high-resolution relevance scores for both […]

Ver mais

The AI vibe decay problem is not a new phenomenon, but AI tooling has supercharged it. The marginal cost of producing a polished interface, a compelling demo, and a well-written landing page has collapsed. The marginal cost of building something people actually want, use, and return to has not. So we have a glut of beautiful apps with no users.

Ver mais

arXiv:2601.15390v1 Announce Type: new Abstract: Unified multimodal models (UMMs) are emerging as strong foundation models that can do both generation and understanding tasks in a single architecture. However, they are typically trained in centralized settings where all training and downstream datasets are gathered in a central server, limiting the deployment in privacy-sensitive and geographically distributed scenarios. In this paper, we present FedUMM, a general federated learning framework for UMMs under non-IID multimodal data with low communication cost. Built […]

Ver mais

arXiv:2602.04893v1 Announce Type: new Abstract: Uncovering the mechanisms behind “jailbreaks” in large language models (LLMs) is crucial for enhancing their safety and reliability, yet these mechanisms remain poorly understood. Existing studies predominantly analyze jailbreak prompts by probing latent representations, often overlooking the causal relationships between interpretable prompt features and jailbreak occurrences. In this work, we propose Causal Analyst, a framework that integrates LLMs into data-driven causal discovery to identify the direct causes of jailbreaks and leverage them for […]

Ver mais

Purpose: Hospital out-patient departments (OPDs) in India face severe queue inefficiencies with average waiting times of 90+ minutes and poor patient communication. Methodology: This study presents MediQueue — a full-stack intelligent queue management system built with React.js, Node.js, MySQL, Socket.io, and a self-learning ML engine. A dual-prediction architecture (Random Forest + equal-distribution fallback) predicts per-department wait times. A nightly recalibration scheduler updates slot capacities from verified treatment records. Findings: The system achieves a Mean Absolute Error (MAE) of […]

Ver mais

arXiv:2603.20335v1 Announce Type: new Abstract: The Interest Public Group ARRONAX’s C70XP cyclotron, used for radioisotope production for medical and research applications, relies on complex and costly systems that are prone to failures, leading to operational disruptions. In this context, this study aims to develop a machine learning-based method for early anomaly detection, from sensor measurements over a temporal window, to enhance system performance. One of the most widely recognized methods for anomaly detection is Isolation Forest (IF), known […]

Ver mais