activity
20242026
collaborators

14 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.LG2026

Parity, Sensitivity, and Transformers

Alexander Kozachinskiy, Tomasz Steifer, Przemysław Wałȩga

Understanding what neural architectures can and cannot compute is a central challenge in the theory of AI. One of the fundamental problems in this context is the PARITY task, which…

cs.LG2026

Message Passing on the Edge: Towards Scalable and Expressive GNNs

Pablo Barceló, Fabian Jogl, Alexander Kozachinskiy +3

Graph neural networks (GNNs) are widely used in graph learning and most architectures propagate information by passing messages between vertices. In this work, we shift our attenti…

cs.CL2026

Language Generation: Complexity Barriers and Implications for Learning

Marcelo Arenas, Pablo Barceló, Luis Cofré +1

Kleinberg and Mullainathan showed that language generation in the limit is always possible at the level of computability: given enough positive examples, a learner can eventually g…

cs.LG2026

Explaining k-Nearest Neighbors: Abductive and Counterfactual Explanations

Pablo Barceló, Alexander Kozachinskiy, Miguel Romero Orth +2

Despite the wide use of -Nearest Neighbors as classification models, their explainability properties remain poorly understood from a theoretical perspective. While nearest neigh…

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…