Vicente Balmaseda

I am a PhD student at the OptMAI Lab in the Department of Computer Science & Engineering at Texas A&M University, where I am advised by Dr. Tianbao Yang.

I hold an MS in Computer Science from Texas A&M University, as well as dual Bachelor's degrees in Telecommunications Engineering and Business Analytics from ICAI, Comillas Pontificial University.

Research

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

	Discovering Global False Negatives On the Fly for Self-supervised Contrastive Learning Vicente Balmaseda, Bokun Wang, Ching-Long Lin, Tianbao Yang Accepted to Forty-second International Conference on Machine Learning (ICML 2025), 2025 code / arXiv / 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 Siqi Guo, Ilgee Hong, Vicente Balmaseda, Changlong Yu, Liang Qiu, Xin Liu, Haoming Jiang, Tuo Zhao, Tianbao Yang Accepted to Forty-second International Conference on Machine Learning (ICML 2025), 2025 code / arXiv / 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.
	Combinatorial Approximations for Cluster Deletion: Simpler, Faster, and Better Vicente Balmaseda, Ying Xu, Yixin Cao, Nate Veldt Forty-first International Conference on Machine Learning (ICML 2024), 2024 paper / code / poster / arXiv / venue / 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 Vicente Balmaseda, María Coronado, Gonzalo de Cadenas-Santiago Intelligent Systems with Applications, 2023 paper / code / 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.