Anyone who works with PyTorch model code starts asking the same questions: Why is this taking so long? How do I make my training loop faster? Whether you’re an ML engineer, a researcher or just decided to play around with a random ML repository over the weekend, you will eventually try to understand how to speed your code up. However, before we can do that, we need to learn how to measure performance correctly. And then draw the […]

Ver mais

arXiv:2604.15415v1 Announce Type: new Abstract: Large language models (LLMs) have evolved into autonomous agents that rely on open skill ecosystems (e.g., ClawHub and Skills.Rest), hosting numerous publicly reusable skills. Existing security research on these ecosystems mainly focuses on vulnerabilities within skills, such as prompt injection. However, there is a critical gap regarding skills that may be misused for harmful actions (e.g., cyber attacks, fraud and scams, privacy violations, and sexual content generation), namely harmful skills. In this paper, […]

Ver mais

Logging is the heartbeat of a production application. In the early days of a project, a simple dev.log tail is sufficient. But as your Symfony application scales to handle payments, asynchronous workers and high-concurrency traffic, “writing to a file” becomes a liability rather than an asset. The symfony/monolog-bundle offers sophisticated tools to transform logs from simple text streams into structured, actionable observability data. This guide explores 10 advanced logging patterns that go beyond the defaults. We will use strict typing, PHP Attributes, and modern YAML configuration. […]

Ver mais

Machine unlearning aims to remove the influence of specific training data from a learned model without full retraining. While recent work has begun to explore unlearning in quantum machine learning, existing approaches largely rely on fixed, uniform target distributions and do not explicitly control the trade-off between forgetting and retained model behaviour. In this work, we propose a distribution-guided framework for class-level quantum machine unlearning that treats unlearning as a constrained optimization problem. Our method introduces a tunable […]

Ver mais

arXiv:2601.15311v1 Announce Type: new Abstract: Large Language Models (LLMs) are fundamentally constrained by the quadratic computational cost of self-attention and the “Lost in the Middle” phenomenon, where reasoning capabilities degrade as context windows expand. Existing solutions, primarily “Flat RAG” architectures relying on vector databases, treat memory as an unstructured bag of embeddings. This approach fails to capture the hierarchical and temporal structure of long-horizon interactions, leading to “Vector Haze”, the retrieval of disjointed facts lacking episodic continuity. We […]

Ver mais

arXiv:2601.14299v1 Announce Type: new Abstract: Network defenders face a steady stream of attacks, observed as raw Intrusion Detection System (IDS) alerts. The sheer volume of alerts demands prioritization, typically based on high-level risk classifications. This work expands the scope of risk measurement by examining alerts not only through their technical characteristics but also by examining and classifying their temporal patterns. One critical issue in responding to intrusion alerts is determining whether an alert is part of an escalating […]

Ver mais

Energy theft poses a significant threat to the stability and efficiency of smart grids, leading to substantial economic losses and operational challenges. Traditional centralized machine learning approaches for theft detection require aggregating user data, raising serious concerns about privacy and data security. These issues are further exacerbated in smart meter environments, where devices are often resource-constrained and lack the capacity to run heavy models. In this work, we propose a privacy-preserving federated learning framework for energy theft detection […]

Ver mais

I. The “Complete System” Fallacy 1.1 The Problem The pursuit of ethical Artificial Intelligence (AI) has been defined by a single, implicit ambition: the creation of a “complete” ethical machine. This is the dream of building an autonomous system whose internal logic, training data, and reward functions are comprehensive enough to resolve any moral dilemma it encounters without human intervention. From the rigid rule-sets of symbolic AI to the “aligned” reinforcement learning models of today, the governing philosophy […]

Ver mais

arXiv:2602.06252v1 Announce Type: new Abstract: The performance gains obtained by large language models (LLMs) are closely linked to their substantial computational and memory requirements. Quantized LLMs offer significant advantages with extremely quantized models, motivating the development of specialized architectures to accelerate their workloads. This paper proposes D-Legion, a novel scalable many-core architecture, designed using many adaptive-precision systolic array cores, to accelerate matrix multiplication in quantized LLMs. The proposed architecture consists of a set of Legions where each Legion […]

Ver mais

arXiv:2601.02375v1 Announce Type: new Abstract: High enrollment in STEM-related degree programs has created increasing demand for scalable tutoring support, as universities experience a shortage of qualified instructors and teaching assistants (TAs). To address this challenge, LeafTutor, an AI tutoring agent powered by large language models (LLMs), was developed to provide step-by-step guidance for students. LeafTutor was evaluated through real programming assignments. The results indicate that the system can deliver step-by-step programming guidance comparable to human tutors. This work […]

Ver mais