Anton Razzhigaev

31 papers A* 1Journal 18Unranked 12
YearRankTypeTitle / Venue / Authors
2026 A* conf
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders.
AAAI
Andrey V. Galichin, Alexey Dontsov, Polina Druzhinina, Anton Razzhigaev, Oleg Rogov, Elena Tutubalina, Ivan V. Oseledets
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 J jnl
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders.
CoRR
Andrey V. Galichin, Alexey Dontsov, Polina Druzhinina, Anton Razzhigaev, Oleg Y. Rogov, Elena Tutubalina, Ivan V. Oseledets
2025 J jnl
Inverting Black-Box Face Recognition Systems via Zero-Order Optimization in Eigenface Space.
CoRR
Anton Razzhigaev, Matvey Mikhalchuk, Klim Kireev, Igor Udovichenko, Andrey Kuznetsov, Aleksandr Petiushko
2025 — conf
LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers.
NAACL (Findings)
Anton Razzhigaev, Matvey Mikhalchuk, Temurbek Rahmatullaev, Elizaveta Goncharova, Polina Druzhinina, Ivan V. Oseledets, Andrey Kuznetsov
2025 J jnl
LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers.
CoRR
Anton Razzhigaev, Matvey Mikhalchuk, Temurbek Rahmatullaev, Elizaveta Goncharova, Polina Druzhinina, Ivan V. Oseledets, Andrey Kuznetsov
2025 J jnl
MindShift: Analyzing Language Models' Reactions to Psychological Prompts.
CoRR
Anton Vasiliuk, Irina Abdullaeva, Polina Druzhinina, Anton Razzhigaev, Andrey Kuznetsov
2025 J jnl
Real-World Transferable Adversarial Attack on Face-Recognition Systems.
CoRR
Andrey Kaznacheev, Matvey Mikhalchuk, Andrey Kuznetsov, Aleksandr Petiushko, Anton Razzhigaev
2025 J jnl
SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens.
CoRR
Nikita Dragunov, Temurbek Rahmatullaev, Elizaveta Goncharova, Andrey Kuznetsov, Anton Razzhigaev
2025 — conf
Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images.
NAACL (Student Research Workshop)
Elisei Rykov, Kseniia Petrushina, Kseniia Titova, Anton Razzhigaev, Alexander Panchenko, Vasily Konovalov
2025 J jnl
Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images.
CoRR
Elisei Rykov, Kseniia Petrushina, Kseniia Titova, Anton Razzhigaev, Alexander Panchenko, Vasily Konovalov
2025 J jnl
Universal Adversarial Attack on Aligned Multimodal LLMs.
CoRR
Temurbek Rahmatullaev, Polina Druzhinina, Matvey Mikhalchuk, Andrey Kuznetsov, Anton Razzhigaev
2024 J jnl
OmniFusion Technical Report.
CoRR
Elizaveta Goncharova, Anton Razzhigaev, Matvey Mikhalchuk, Maxim Kurkin, Irina Abdullaeva, Matvey Skripkin, Ivan V. Oseledets, Denis Dimitrov, Andrey Kuznetsov
2024 — conf
The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models.
EACL (Findings)
Anton Razzhigaev, Matvey Mikhalchuk, Elizaveta Goncharova, Ivan V. Oseledets, Denis Dimitrov, Andrey Kuznetsov
2024 — conf
Your Transformer is Secretly Linear.
ACL (1)
Anton Razzhigaev, Matvey Mikhalchuk, Elizaveta Goncharova, Nikolai Gerasimenko, Ivan V. Oseledets, Denis Dimitrov, Andrey Kuznetsov
2024 J jnl
Your Transformer is Secretly Linear.
CoRR
Anton Razzhigaev, Matvey Mikhalchuk, Elizaveta Goncharova, Nikolai Gerasimenko, Ivan V. Oseledets, Denis Dimitrov, Andrey Kuznetsov
2023 — conf
A System for Answering Simple Questions in Multiple Languages.
ACL (demo)
Anton Razzhigaev, Mikhail Salnikov, Valentin Malykh, Pavel Braslavski, Alexander Panchenko
2023 — conf
Answer Candidate Type Selection: Text-To-Text Language Model for Closed Book Question Answering Meets Knowledge Graphs.
KONVENS
Mikhail Salnikov, Maria Lysyuk, Pavel Braslavski, Anton Razzhigaev, Valentin Malykh, Alexander Panchenko
2023 J jnl
Answer Candidate Type Selection: Text-to-Text Language Model for Closed Book Question Answering Meets Knowledge Graphs.
CoRR
Mikhail Salnikov, Maria Lysyuk, Pavel Braslavski, Anton Razzhigaev, Valentin Malykh, Alexander Panchenko
2023 — conf
Kandinsky: An Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion.
EMNLP (Demos)
Anton Razzhigaev, Arseniy Shakhmatov, Anastasia Maltseva, Vladimir Arkhipkin, Igor Pavlov, Ilya Ryabov, Angelina Kuts, Alexander Panchenko, Andrey Kuznetsov, Denis Dimitrov
2023 J jnl
Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion.
CoRR
Anton Razzhigaev, Arseniy Shakhmatov, Anastasia Maltseva, Vladimir Arkhipkin, Igor Pavlov, Ilya Ryabov, Angelina Kuts, Alexander Panchenko, Andrey Kuznetsov, Denis Dimitrov
2023 J jnl
On Isotropy of Multimodal Embeddings.
Inf.
Kirill Tyshchuk, Polina Karpikova, Andrew Spiridonov, Anastasiia Prutianova, Anton Razzhigaev, Alexander Panchenko
2023 J jnl
The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models.
CoRR
Anton Razzhigaev, Matvey Mikhalchuk, Elizaveta Goncharova, Ivan V. Oseledets, Denis Dimitrov, Andrey Kuznetsov
2022 — conf
MEKER: Memory Efficient Knowledge Embedding Representation for Link Prediction and Question Answering.
ACL (student)
Viktoria Chekalina, Anton Razzhigaev, Albert Sayapin, Evgeny Frolov, Alexander Panchenko
2022 J jnl
MEKER: Memory Efficient Knowledge Embedding Representation for Link Prediction and Question Answering.
CoRR
Viktoria Chekalina, Anton Razzhigaev, Albert Sayapin, Alexander Panchenko
2022 — conf
Ranking Approach to Monolingual Question Answering over Knowledge Graphs.
NLIWoD@ESWC
Nikita Baramiia, Alina Rogulina, Sergey Petrakov, Valerii Kornilov, Anton Razzhigaev
2021 J jnl
Darker than Black-Box: Face Reconstruction from Similarity Queries.
CoRR
Anton Razzhigaev, Klim Kireev, Igor Udovichenko, Aleksandr Petiushko
2021 — conf
SkoltechNLP at SemEval-2021 Task 2: Generating Cross-Lingual Training Data for the Word-in-Context Task.
SemEval@ACL/IJCNLP
Anton Razzhigaev, Nikolay Arefyev, Alexander Panchenko
2020 — conf
Black-Box Face Recovery from Identity Features.
ECCV Workshops (5)
Anton Razzhigaev, Klim Kireev, Edgar Kaziakhmedov, Nurislam Tursynbek, Aleksandr Petiushko
2020 J jnl
Black-Box Face Recovery from Identity Features.
CoRR
Anton Razzhigaev, Klim Kireev, Edgar Kaziakhmedov, Nurislam Tursynbek, Aleksandr Petiushko