activity
20232026
collaborators

6 papers

cs.LG2026

Indexing: the Beginning and the End

Alexander Kozachinskiy, Vicente Opazo, Felipe Urrutia

We study information bottlenecks in modern deep-learning architectures -- RNNs, softmax transformers, linear-attention transformers and state-space models -- through the lens of th…

cs.LG2025

Decoupling Positional and Symbolic Attention Behavior in Transformers

Felipe Urrutia, Jorge Salas, Alexander Kozachinskiy +3

An important aspect subtending language understanding and production is the ability to independently encode positional and symbolic information of the words within a sentence. In T…

cs.LG2025

Continuity and Isolation Lead to Doubts or Dilemmas in Large Language Models

Hector Pasten, Felipe Urrutia, Hector Jimenez +3

Understanding how Transformers work and how they process information is key to the theoretical and empirical advancement of these machines. In this work, we demonstrate the existen…

cs.LG2025

Zero-Shot Decision Tree Construction via Large Language Models

Lucas Carrasco, Felipe Urrutia, Andrés Abeliuk

This paper introduces a novel algorithm for constructing decision trees using large language models (LLMs) in a zero-shot manner based on Classification and Regression Trees (CART)…

cs.LG2025

Strassen Attention, Split VC Dimension and Compositionality in Transformers

Alexander Kozachinskiy, Felipe Urrutia, Hector Jimenez +6

We propose the first method to show theoretical limitations for one-layer softmax transformers with arbitrarily many precision bits (even infinite). We establish those limitations…

cs.CL2023

Deep Natural Language Feature Learning for Interpretable Prediction

Felipe Urrutia, Cristian Buc, Valentin Barriere

We propose a general method to break down a main complex task into a set of intermediary easier sub-tasks, which are formulated in natural language as binary questions related to t…