Blog

I am very happy to share three recent accepted publications from 2026:

1. MATH-PT: A Math Reasoning Benchmark for European and Brazilian Portuguese #

Authors: Tiago Teixeira, Ana Carolina Erthal, Juan Belieni, Beatriz Canaverde, Miguel Faria, Diego Mesquita, Eliezer de Souza da Silva, André Martins
Venue: 17th Conference on Computational Processing of Portuguese (PROPOR 2026)

Divergence Training for Generative Models #

0. Loss Design, Policy Gradients, and On/Off-Policy Optimization #

Over the last few years, several machine learning communities have converged on a common mathematical structure underlying many training algorithms:

I am delighted to announce that our paper, When do GFlowNets Learn the Right Distribution?, has been accepted for presentation at ICLR 2025! This work advances our theoretical understanding of Generative Flow Networks (GFlowNets) by examining the impact of balance violations on their ability to approximate target distributions and proposing a novel metric for assessing correctness.

I am thrilled to share that two of our papers have been accepted at the LatinX in AI Research Workshop at NeurIPS 2024! These works push the boundaries in causal inference and generative modeling, contributing new methodologies and insights to the field.

I’m excited to announce that our paper, “On Divergence Measures for Training GFlowNets,” authored by Tiago da Silva, Eliezer de Souza da Silva, and Diego Mesquita, has been accepted at NeurIPS 2024! 🎉

There is an algorithm to generate Dirichlet samples using a sampler for Gamma distribution for any \( \alpha > 0 \) and \( \beta > 0 \). We will generate Gamma distributed variables \( z_k \sim \text{gamma}(\alpha_k,1) \), for \( k \in {1,\cdots,d} \), and do the following variable transformation to get Dirichlet samples \( x_k = \frac{z_k}{\sum_k z_k} \). First, we should demonstrate that this transformation results in Dirichlet distributed samples.