Laida Kushnareva

23 papers A* 2A 1Journal 14Unranked 6
YearRankTypeTitle / Venue / Authors
2026 — conf
AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders.
EACL (Volume 1: Long Papers)
Georgii Aparin, Tasnima Sadekova, Alexey D. Rukhovich, Assel Yermekova, Laida Kushnareva, Vadim Popov, Kristian Kuznetsov, Irina Piontkovskaya
2026 J jnl
AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders.
CoRR
Georgii Aparin, Tasnima Sadekova, Alexey D. Rukhovich, Assel Yermekova, Laida Kushnareva, Vadim Popov, Kristian Kuznetsov, Irina Piontkovskaya
2026 — conf
Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story.
EACL (Volume 1: Long Papers)
Vladislav Pedashenko, Laida Kushnareva, Yana Khassan Nibal, Eduard Tulchinskii, Kristian Kuznetsov, Vladislav Zharchinskii, Yury Maximov, Irina Piontkovskaya
2025 — conf
Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders.
ACL (Findings)
Kristian Kuznetsov, Laida Kushnareva, Anton Razzhigaev, Polina Druzhinina, Anastasia Voznyuk, Irina Piontkovskaya, Evgeny Burnaev, Serguei Barannikov
2025 J jnl
Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders.
CoRR
Kristian Kuznetsov, Laida Kushnareva, Polina Druzhinina, Anton Razzhigaev, Anastasia Voznyuk, Irina Piontkovskaya, Evgeny Burnaev, Serguei Barannikov
2025 A* conf
Quantifying Logical Consistency in Transformers via Query-Key Alignment.
EMNLP
Eduard Tulchinskii, Laida Kushnareva, Anastasia Voznyuk, Andrei Andriiainen, Irina Piontkovskaya, Evgeny Burnaev, Serguei Barannikov
2025 J jnl
Quantifying Logical Consistency in Transformers via Query-Key Alignment.
CoRR
Eduard Tulchinskii, Anastasia Voznyuk, Laida Kushnareva, Andrei Andriiainen, Irina Piontkovskaya, Evgeny Burnaev, Serguei Barannikov
2025 J jnl
Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story.
CoRR
Vladislav Pedashenko, Laida Kushnareva, Yana Khassan Nibal, Eduard Tulchinskii, Kristian Kuznetsov, Vladislav Zharchinskii, Yury Maximov, Irina Piontkovskaya
2024 J jnl
Improving Interpretability and Robustness for the Detection of AI-Generated Images.
CoRR
Tatiana Gaintseva, Laida Kushnareva, German Magai, Irina Piontkovskaya, Sergey I. Nikolenko, Martin Benning, Serguei Barannikov, Gregory G. Slabaugh
2024 J jnl
Listening to the Wise Few: Select-and-Copy Attention Heads for Multiple-Choice QA.
CoRR
Eduard Tulchinskii, Laida Kushnareva, Kristian Kuznetsov, Anastasia Voznyuk, Andrei Andriiainen, Irina Piontkovskaya, Evgeny Burnaev, Serguei Barannikov
2024 — conf
Robust AI-Generated Text Detection by Restricted Embeddings.
EMNLP (Findings)
Kristian Kuznetsov, Eduard Tulchinskii, Laida Kushnareva, German Magai, Serguei Barannikov, Sergey I. Nikolenko, Irina Piontkovskaya
2024 J jnl
Robust AI-Generated Text Detection by Restricted Embeddings.
CoRR
Kristian Kuznetsov, Eduard Tulchinskii, Laida Kushnareva, German Magai, Serguei Barannikov, Sergey I. Nikolenko, Irina Piontkovskaya
2023 J jnl
Artificial Text Boundary Detection with Topological Data Analysis and Sliding Window Techniques.
CoRR
Laida Kushnareva, Tatiana Gaintseva, German Magai, Serguei Barannikov, Dmitry Abulkhanov, Kristian Kuznetsov, Irina Piontkovskaya, Sergey I. Nikolenko
2023 A* conf
Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts.
NeurIPS
Eduard Tulchinskii, Kristian Kuznetsov, Laida Kushnareva, Daniil Cherniavskii, Sergey I. Nikolenko, Evgeny Burnaev, Serguei Barannikov, Irina Piontkovskaya
2023 J jnl
Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts.
CoRR
Eduard Tulchinskii, Kristian Kuznetsov, Laida Kushnareva, Daniil Cherniavskii, Serguei Barannikov, Irina Piontkovskaya, Sergey I. Nikolenko, Evgeny Burnaev
2023 A conf
Topological Data Analysis for Speech Processing.
INTERSPEECH
Eduard Tulchinskii, Kristian Kuznetsov, Laida Kushnareva, Daniil Cherniavskii, Serguei Barannikov, Irina Piontkovskaya, Sergey I. Nikolenko, Evgeny Burnaev
2022 — conf
Acceptability Judgements via Examining the Topology of Attention Maps.
EMNLP (Findings)
Daniil Cherniavskii, Eduard Tulchinskii, Vladislav Mikhailov, Irina Proskurina, Laida Kushnareva, Ekaterina Artemova, Serguei Barannikov, Irina Piontkovskaya, Dmitri Piontkovski, Evgeny Burnaev
2022 J jnl
Acceptability Judgements via Examining the Topology of Attention Maps.
CoRR
Daniil Cherniavskii, Eduard Tulchinskii, Vladislav Mikhailov, Irina Proskurina, Laida Kushnareva, Ekaterina Artemova, Serguei Barannikov, Irina Piontkovskaya, Dmitri Piontkovski, Evgeny Burnaev
2022 J jnl
Betti numbers of attention graphs is all you really need.
CoRR
Laida Kushnareva, Dmitri Piontkovski, Irina Piontkovskaya
2022 J jnl
Topological Data Analysis for Speech Processing.
CoRR
Eduard Tulchinskii, Kristian Kuznetsov, Laida Kushnareva, Daniil Cherniavskii, Serguei Barannikov, Irina Piontkovskaya, Sergey I. Nikolenko, Evgeny Burnaev
2021 — conf
Artificial Text Detection via Examining the Topology of Attention Maps.
EMNLP (1)
Laida Kushnareva, Daniil Cherniavskii, Vladislav Mikhailov, Ekaterina Artemova, Serguei Barannikov, Alexander Bernstein, Irina Piontkovskaya, Dmitri Piontkovski, Evgeny Burnaev
2021 J jnl
Artificial Text Detection via Examining the Topology of Attention Maps.
CoRR
Laida Kushnareva, Daniil Cherniavskii, Vladislav Mikhailov, Ekaterina Artemova, Serguei Barannikov, Alexander Bernstein, Irina Piontkovskaya, Dmitri Piontkovski, Evgeny Burnaev
2020 J jnl
Category-Learning with Context-Augmented Autoencoder.
CoRR
Denis Kuzminykh, Laida Kushnareva, Timofey Grigoryev, Alexander Zatolokin