collaborators

6 papers

cs.LG2026

ChronoVAE-HOPE: Beyond Attention -- A Next-Generation VAE Foundation Model for Specialized Time Series Classification

José Alberto Rodríguez, Luis Balderas, Miguel Lastra +2

Time Series Foundation Models (TSFMs) have become a new component of the state-of-the-art in general time series forecasting. However, adapting them to specialized classification t…

cs.LG2026

KairosHope: A Next-Generation Time-Series Foundation Model for Specialized Classification via Dual-Memory Architecture

Luis Balderas, José Alberto Rodríguez, Miguel Lastra +2

Time Series Foundation Models (TSFMs) have demonstrated notable success in general-purpose forecasting tasks; however, their adaptation to specialized classification problems remai…

cs.LG2026

MoEITS: A Green AI approach for simplifying MoE-LLMs

Luis Balderas, Miguel Lastra, José M. Benítez

Large language models are transforming all areas of academia and industry, attracting the attention of researchers, professionals, and the general public. In the trek for more powe…

cs.CV2023

Optimizing Convolutional Neural Network Architecture

Luis Balderas, Miguel Lastra, José M. Benítez

Convolutional Neural Networks (CNN) are widely used to face challenging tasks like speech recognition, natural language processing or computer vision. As CNN architectures get larg…

cs.LG2023

Can persistent homology whiten Transformer-based black-box models? A case study on BERT compression

Luis Balderas, Miguel Lastra, José M. Benítez

Large Language Models (LLMs) like BERT have gained significant prominence due to their remarkable performance in various natural language processing tasks. However, they come with…

cs.LG2023

Optimizing Dense Feed-Forward Neural Networks

Luis Balderas, Miguel Lastra, José M. Benítez

Deep learning models have been widely used during the last decade due to their outstanding learning and abstraction capacities. However, one of the main challenges any scientist ha…