collaborators

5 papers

cs.CL2025

Amadeus-Verbo Technical Report: The powerful Qwen2.5 family models trained in Portuguese

William Alberto Cruz-Castañeda, Marcellus Amadeus

This report introduces the experience of developing Amadeus Verbo, a family of large language models for Brazilian Portuguese. To handle diverse use cases, Amadeus Verbo includes b…

cs.CL2024

Evaluation Metrics for Text Data Augmentation in NLP

Marcellus Amadeus, William Alberto Cruz Castañeda

Recent surveys on data augmentation for natural language processing have reported different techniques and advancements in the field. Several frameworks, tools, and repositories pr…

cs.CL2024

Phonetically rich corpus construction for a low-resourced language

Marcellus Amadeus, William Alberto Cruz Castañeda, Wilmer Lobato +1

Speech technologies rely on capturing a speaker's voice variability while obtaining comprehensive language information. Textual prompts and sentence selection methods have been pro…

cs.CV2024

Image captioning for Brazilian Portuguese using GRIT model

Rafael Silva de Alencar, William Alberto Cruz Castañeda, Marcellus Amadeus

This work presents the early development of a model of image captioning for the Brazilian Portuguese language. We used the GRIT (Grid - and Region-based Image captioning Transforme…

cs.CV2024

An Inpainting-Infused Pipeline for Attire and Background Replacement

Felipe Rodrigues Perche-Mahlow, André Felipe-Zanella, William Alberto Cruz-Castañeda +1

In recent years, groundbreaking advancements in Generative Artificial Intelligence (GenAI) have triggered a transformative paradigm shift, significantly influencing various domains…