activity
20202026
most citedLogical Languages Accepted by Transformer Encoders with Hard Attention

2 citations · 2 across the 5 of their papers we have counts for

collaborators

6 papers

cs.CC2026

Polynomial-Time Mistake-Bounded Language Generation

Héctor Jimenez, Alexander Kozachinskiy, Vicente Opazo

In this paper, we introduce a polynomial-time version of the mistake-bounded language generation (MBLG) framework due to Kleinberg, Peale, and Reingold (2026). We obtain upper and…

cs.CL2025

The Counting Power of Transformers

Marco Sälzer, Chris Köcher, Alexander Kozachinskiy +2

Counting properties (e.g. determining whether certain tokens occur more than other tokens in a given input text) have played a significant role in the study of expressiveness of tr…

cs.CC2023

Towards Simpler Sorting Networks and Monotone Circuits for Majority

Natalia Dobrokhotova-Maikova, Alexander Kozachinskiy, Vladimir Podolskii

In this paper, we study the problem of computing the majority function by low-depth monotone circuits and a related problem of constructing low-depth sorting networks. We consider…

cs.FL2023★ 2 cited

Logical Languages Accepted by Transformer Encoders with Hard Attention

Pablo Barcelo, Alexander Kozachinskiy, Anthony Widjaja Lin +1

We contribute to the study of formal languages that can be recognized by transformer encoders. We focus on two self-attention mechanisms: (1) UHAT (Unique Hard Attention Transforme…

cs.CC2022

Constant-Depth Sorting Networks

Natalia Dobrokhotova-Maikova, Alexander Kozachinskiy, Vladimir Podolskii

In this paper, we address sorting networks that are constructed from comparators of arity . That is, in our setting the arity of the comparators -- or, in other words, the n…

cs.CC2020

Multiparty Karchmer-Wigderson Games and Threshold Circuits

Alexander Kozachinskiy, Vladimir Podolskii

We suggest a generalization of Karchmer-Wigderson communication games to the multiparty setting. Our generalization turns out to be tightly connected to circuits consisting of thre…