large language models

Best-of-N: Inference-Time Compute for Small Language Models

Technical note TR-2026-02, superseding TR-2026-01. We measure what happens when a frozen language model is sampled 128 times perproblem and the result is selected rather than taken as given. On GSM8K,Qwen2.5-0.5B-Instruct goes from 45.3% at a single sample to 66.5% undermajority voting, with no weights modified. Covera...

DOACT.Vasc Study

The project was conceived and developed based on an automated computational flowchart structured through a decision tree using the CART (Classification and Regression Tree) method, and it was approved by the Ethics Committee of Santa Casa de São Paulo. The resulting algorithm, named DOACT, was fully documented and made...

MACHINE LEARNING FOR CYBERSECURITY: ADVERSARIAL ATTACKS AND DEFENSE

FUNDAMENTALS OF MACHINE LEARNING At the heart of digital transformation lies machine learning, a pivotal technology that shapes the course of innovation. Essentially, machine learning enables computers to learn from data and make independent decisions without needing specific programming instructions .For individuals a...

MACHINE LEARNING FOR CYBERSECURITY: ADVERSARIAL ATTACKS AND DEFENSE

FUNDAMENTALS OF MACHINE LEARNING At the heart of digital transformation lies machine learning, a pivotal technology that shapes the course of innovation. Essentially, machine learning enables computers to learn from data and make independent decisions without needing specific programming instructions .For individuals a...

Beyond Empathy: Emotional Intelligence and Artificial Intelligence in Clinical Social Work Practice, Therapeutic Alliance and Human Services

Artificial intelligence possesses growing capacity to recognize, interpret, and simulate emotional responses, but core dimensions of emotional intelligence—including authentic empathy, moral reasoning, contextual judgment, cultural responsiveness, and relational attunement—remain fundamentally human competencies.

Threads That Hold: Building a Community Cancer Care Ecosystem in a Border Region.

The THREADS Framework is introduced, a practical model for health services leaders comprising Trust, Hub-and-spoke anchoring, Routine screening, Embedded partnerships, Aligned navigation, Data that reflects reality, and Sustainability and stewardship.

A Large Language Model-enhanced Delay-and-Sum algorithm for damage imaging in carbon fiber reinforced polymer composites

Large-language-model-driven multiple algorithm evolution for network-constrained unit commitment model reduction

LLM-Assisted Behavioural and Scenario Augmentation for Agent-Based Energy Adoption Models

A hybrid framework for LLM-assisted specification design, integrating bounded behavioural rubrics and structured scenario specifications into a calibrated agent-based model (ABM) of solar photovoltaic adoption by Irish dairy farms achieves up to approximately 13% behavioural adoption increase relative to the correspond...

Personalized Recommendation Tool Learning via Autonomous Language Agents

An agent-based recommendation framework, memory-based Personalized Recommendation Tool learning via autonomous language Agents (PRTA), in which an LLM acts as a central planner interacting with multiple recommendation models as tools, demonstrating the superiority of PRTA over traditional recommendation and LLM-based b...

EuLLM — Open-source sovereign LLM platform

EuLLM is an open-source platform for creating, distributing, and running sovereign EU-compliant Large Language Models, designed for verticalization across domains, languages, and brands while ensuring AI Act compliance. The platform consists of three components: Engine — a Rust-based inference runtime built on top of l...

Continuously Adaptive Curricula: Using Learner Models to Restructure Instruction in Real Time

Large language models can generate explanations and tutoring dialogue on demand, but most systems still rely on a curriculum that was fixed at the start of learning. The result is a path that does not change when a learner masters material early or repeatedly struggles with a prerequisite. This paper argues that the mo...