2 papers
cs.CV2026
ViT-Explainer: An Interactive Walkthrough of the Vision Transformer Pipeline
Juan Manuel Hernandez, Mariana Fernandez-Espinosa, Denis Parra +1
Transformer-based architectures have become the shared backbone of natural language processing and computer vision. However, understanding how these models operate remains challeng…
cs.LG2025
A Compressive-Expressive Communication Framework for Compositional Representations
Rafael Elberg, Felipe del Rio, Mircea Petrache +1
Compositionality in knowledge and language--the ability to represent complex concepts as a combination of simpler ones--is a hallmark of human cognition and communication. Despite…