Vicente Balmaseda

I am a PhD student at the OptMAI Lab, part of the Department of Computer Science & Engineering at Texas A&M University. My PhD advisor is Tianbao Yang.

I have an MS in Computer Science from Texas A&M University. I have a Bachelor's in Telecommunications Engineering and a Bachelor's in Business Analytics from ICAI.

Research

I'm interested in deep learning, machine learning, graph analytics, and their practical applications.

Combinatorial Approximations for Cluster Deletion: Simpler, Faster, and Better

We provide improved deterministic approximation algorithms and guarantees for Cluster Deletion, and the first combinatorial algorithm for the Strong Triadic Closure (STC) relaxation.

Predicting systemic risk in financial systems using Deep Graph Learning

We propose Graph Neural Networks (GNNs) for systemic risk analysis in financial networks, leveraging network structure to overcome ML limitations. Additionally, we introduce C2R approach to reduce pre-labeling efforts for costly continuous systemic risk metrics, enabling modeling these metrics (e.g., quantiles) using data labeled into just a few classes.

Preprints

Discovering Global False Negatives On the Fly for Self-supervised Contrastive Learning

We introduce GloFND, an optimization-based approach for false negative discovery in self-supervised unimodal and bimodal contrastive learning. GloFND globally detects false negatives across the entire dataset while maintaining a per-iteration computation cost independent of dataset size.

Discriminative Finetuning of Generative Large Language Models without Reward Models and Preference Data

We introduce Discriminative Fine-Tuning (DFT), an approach for fine-tuning LLMs without preference data or reward models. Unlike Supervised Fine-Tuning (SFT), DFT adopts a discriminative paradigm to efficiently optimize the likelihood of an answer among all possible outputs given an input.

Other Projects

These include coursework and side projects.

TransformerKart: A Full SuperTuxKart AI Controller

Deep SuperTuxKart AI

Updated on February 2025

Design and source code from Leonid Keselman's website