no code implementations • 14 Nov 2023 • Laida Kushnareva, Tatiana Gaintseva, German Magai, Serguei Barannikov, Dmitry Abulkhanov, Kristian Kuznetsov, Eduard Tulchinskii, Irina Piontkovskaya, Sergey Nikolenko
Due to the rapid development of large language models, people increasingly often encounter texts that may start as written by a human but continue as machine-generated.
no code implementations • 24 Aug 2023 • Nikita Balabin, Daria Voronkova, Ilya Trofimov, Evgeny Burnaev, Serguei Barannikov
We propose TopDis (Topological Disentanglement), a method for learning disentangled representations via adding multi-scale topological loss term.
1 code implementation • NeurIPS 2023 • Eduard Tulchinskii, Kristian Kuznetsov, Laida Kushnareva, Daniil Cherniavskii, Serguei Barannikov, Irina Piontkovskaya, Sergey Nikolenko, Evgeny Burnaev
Rapidly increasing quality of AI-generated content makes it difficult to distinguish between human and AI-generated texts, which may lead to undesirable consequences for society.
1 code implementation • 31 Jan 2023 • Ilya Trofimov, Daniil Cherniavskii, Eduard Tulchinskii, Nikita Balabin, Evgeny Burnaev, Serguei Barannikov
The method aims to provide topological similarity between the data manifold and its latent representation via enforcing the similarity in topological features (clusters, loops, 2D voids, etc.)
no code implementations • 30 Nov 2022 • Eduard Tulchinskii, Kristian Kuznetsov, Laida Kushnareva, Daniil Cherniavskii, Serguei Barannikov, Irina Piontkovskaya, Sergey Nikolenko, Evgeny Burnaev
We apply topological data analysis (TDA) to speech classification problems and to the introspection of a pretrained speech model, HuBERT.
1 code implementation • 19 May 2022 • Daniil Cherniavskii, Eduard Tulchinskii, Vladislav Mikhailov, Irina Proskurina, Laida Kushnareva, Ekaterina Artemova, Serguei Barannikov, Irina Piontkovskaya, Dmitri Piontkovski, Evgeny Burnaev
The role of the attention mechanism in encoding linguistic knowledge has received special interest in NLP.
Ranked #1 on Linguistic Acceptability on ItaCoLA
1 code implementation • 31 Dec 2021 • Serguei Barannikov, Ilya Trofimov, Nikita Balabin, Evgeny Burnaev
Comparison of data representations is a complex multi-aspect problem that has not enjoyed a complete solution yet.
no code implementations • 29 Sep 2021 • Serguei Barannikov, Ilya Trofimov, Nikita Balabin, Evgeny Burnaev
We propose a method for comparing two data representations.
2 code implementations • EMNLP 2021 • Laida Kushnareva, Daniil Cherniavskii, Vladislav Mikhailov, Ekaterina Artemova, Serguei Barannikov, Alexander Bernstein, Irina Piontkovskaya, Dmitri Piontkovski, Evgeny Burnaev
The impressive capabilities of recent generative models to create texts that are challenging to distinguish from the human-written ones can be misused for generating fake news, product reviews, and even abusive content.
2 code implementations • NeurIPS 2021 • Serguei Barannikov, Ilya Trofimov, Grigorii Sotnikov, Ekaterina Trimbach, Alexander Korotin, Alexander Filippov, Evgeny Burnaev
We develop a framework for comparing data manifolds, aimed, in particular, towards the evaluation of deep generative models.
1 code implementation • NeurIPS 2021 • Serguei Barannikov, Ilya Trofimov, Grigorii Sotnikov, Ekaterina Trimbach, Alexander Korotin, Alexander Filippov, Evgeny Burnaev
We propose a framework for comparing data manifolds, aimed, in particular, towards the evaluation of deep generative models.
no code implementations • 31 Dec 2020 • Serguei Barannikov, Daria Voronkova, Ilya Trofimov, Alexander Korotin, Grigorii Sotnikov, Evgeny Burnaev
We define the neural network Topological Obstructions score, "TO-score", with the help of robust topological invariants, barcodes of the loss function, that quantify the "badness" of local minima for gradient-based optimization.
no code implementations • 29 Nov 2019 • Serguei Barannikov, Alexander Korotin, Dmitry Oganesyan, Daniil Emtsev, Evgeny Burnaev
We apply the canonical forms (barcodes) of gradient Morse complexes to explore topology of loss surfaces.
no code implementations • 25 Sep 2019 • Serguei Barannikov, Alexander Korotin, Dmitry Oganesyan, Daniil Emtsev, Evgeny Burnaev
We apply canonical forms of gradient complexes (barcodes) to explore neural networks loss surfaces.