Felipe Maia Polo

Recommendations Beyond Catalogs: Diffusion Models for Personalized Generation

arXiv 2025

tinyBenchmarks: evaluating LLMs with fewer examples

arXiv 2024

Efficient multi-prompt evaluation of LLMs

arXiv 2024

LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content

arXiv 2024

Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families

arXiv 2024

Fusing Models with Complementary Expertise

arXiv 2023

LegalNLP -- Natural Language Processing methods for the Brazilian Legal Language

arXiv 2021

Effects of personality traits in predicting grade retention of Brazilian students

arXiv 2021

Mikhail Yurochkin

Yuekai Sun

Leshem Choshen

Jonathan Batista Ferreira

Lucas Weber

Renato Vicente

Allysson Flavio Melo de Oliveira

Antônio Carlos do Amaral Maia

Assaf Arbelle

Carlos Guatimosim