collaborators

7 papers

cs.LG2026

Benford's Law as a Distributional Prior for Post-Training Quantization of Large Language Models

Arthur Negrão, Pedro Silva, Vander L. S. Freitas +2

The rapid growth of Large Language Models (LLMs) intensifies the need for effective compression, with weight quantization being the most widely adopted technique. Standard uniform…

cs.CV2025

PD-Loss: Proxy-Decidability for Efficient Metric Learning

Pedro Silva, Guilherme A. L. Silva, Pablo Coelho +4

Deep Metric Learning (DML) aims to learn embedding functions that map semantically similar inputs to proximate points in a metric space while separating dissimilar ones. Existing m…

cs.LG2025

Deep Learning for School Dropout Detection: A Comparison of Tabular and Graph-Based Models for Predicting At-Risk Students

Pablo G. Almeida, Guilherme A. L. Silva, Valéria Santos +3

Student dropout is a significant challenge in educational systems worldwide, leading to substantial social and economic costs. Predicting students at risk of dropout allows for tim…

cs.NE2025

Enhancing Decision Space Diversity in Multi-Objective Evolutionary Optimization for the Diet Problem

Gustavo V. Nascimento, Ivan R. Meneghini, Valéria Santos +2

Multi-objective evolutionary algorithms (MOEAs) are essential for solving complex optimization problems, such as the diet problem, where balancing conflicting objectives, like cost…

cs.CV2025

Investigating the Impact of Large-Scale Pre-training on Nutritional Content Estimation from 2D Images

Michele Andrade, Guilherme A. L. Silva, Valéria Santos +2

Estimating the nutritional content of food from images is a critical task with significant implications for health and dietary monitoring. This is challenging, especially when rely…

cs.CL2025

MOPrompt: Multi-objective Semantic Evolution for Prompt Optimization

Sara Câmara, Eduardo Luz, Valéria Carvalho +2

Prompt engineering is crucial for unlocking the potential of Large Language Models (LLMs). Still, since manual prompt design is often complex, non-intuitive, and time-consuming, au…