?
Unsupervised Discovery of Interpretable Directions in the GAN Latent Space
P. 9728–9738.
Voynov A., Babenko A.
Dmitry Pronin, Evgeny Kazartsev, Digital Scholarship in the Humanities 2026 P. 1–15
This article repositions Burrows’s Delta as a flexible family of distance measures for exploratory and unsupervised stylometry, where interpretability and stability are as important as predictive accuracy. We introduce two probabilistic extensions, Rank-Turbulence Delta and Jensen–Shannon Delta, by reinterpreting uncentred standardized word-frequency vectors as non-negative representations that can be normalized into probability distributions and compared ...
Added: June 4, 2026
Avdoshin S. M., Pesotskaya E. Y., Информационные технологии 2026 Т. 32 № 4 С. 185–194
With the rapid advancement of artificial intelligence, and deep learning in particular, models have emerged that are capable of delivering highly accurate predictions. However, the internal logic of such models remains difficult to interpret—an issue of critical importance, especially in domains where the correctness of an algorithm directly affects high-stakes decision-making. One promising avenue for ...
Added: May 8, 2026
Balagansky N., Maximov I., Gavrilov D., , in: Proceedings of the 13th International Conference on Learning Representations (ICLR 2025).: ICLR, 2025. P. 57940–57957.
Understanding how features evolve across layers in deep neural networks is a fundamental challenge in mechanistic interpretability, particularly due to polysemanticity and feature superposition. While Sparse Autoencoders (SAEs) have been used to extract interpretable features from individual layers, aligning these features across layers has remained an open problem. In this paper, we introduce SAE Match, ...
Added: February 25, 2026
Anton R., Mikhalchuk M., Rahmatullaev T. et al., , in: Findings of the Association for Computational Linguistics: NAACL 2025.: Association for Computational Linguistics, 2025. P. 7757–7764.
We introduce methods to quantify how Large Language Models (LLMs) encode and store contextual information, revealing that tokens often seen as minor (e.g., determiners, punctuation) carry surprisingly high context. Notably, removing these tokens — especially stopwords, articles, and commas — consistently degrades performance on MMLU and BABILong-4k, even if removing only irrelevant tokens. Our analysis ...
Added: November 6, 2025
Maksimenkova O. V., Сегал А. П., Вопросы философии 2025 № 10 С. 67–76
The study is devoted to the humans and artificial intelligence (AI) interaction. The authors view this interaction as mediated by interfaces that both simplify it and hide the real mechanisms of encoding and decoding messages (according to Shannon). In such a situation, the characteristics of the actor of communication are blurred, and it is not ...
Added: October 2, 2025
Bazhukov M., Voloshina E., Sergey Pletnev et al., , in: Proceedings of the 28th Conference on Computational Natural Language Learning.: Association for Computational Linguistics, 2024. P. 280–290.
Added: March 11, 2025
Sadeghi Z., Alizadehsani R., Cifci M. A. et al., Computers and Electrical Engineering 2024 Vol. 118 No. A Article 109370
Explainable Artificial Intelligence (XAI) encompasses the strategies and methodologies used in constructing AI systems that enable end-users to comprehend and interpret the outputs and predictions made by AI models. The increasing deployment of opaque AI applications in high-stakes fields, particularly healthcare, has amplified the need for clarity and explainability. This stems from the potential high-impact ...
Added: June 8, 2024
Yankovskaya A. E., Gorbunov I. V., Hodashinsky I. A., Pattern Recognition and Image Analysis 2021 Vol. 2 No. 27 P. 243–265
This paper starts a brief historical overview of occurrence and development of fuzzy systems and their applications. Integration methods are proposed to construct a fuzzy system using other AI methods, achieving synergy effect. Accuracy and interpretability are selected as main properties of rule-based fuzzy systems. The tradeoff between interpretability and accuracy is considered to be ...
Added: September 27, 2021
Ratnikov F., Rogachev A., , in: EPJ Web of ConferencesVol. 251: 25th International Conference on Computing in High Energy and Nuclear Physics (CHEP 2021).: EDP Sciences, 2021. Ch. 03043.
Added: September 14, 2021
A. Maevskiy, F. Ratnikov, Zinchenko A. et al., The European Physical Journal C - Particles and Fields 2021 Vol. 81 Article 599
High energy physics experiments rely heavily on the detailed detector simulation models in many tasks. Running these detailed models typically requires a notable amount of the computing time available to the experiments. In this work, we demonstrate a new approach to speed up the simulation of the Time Projection Chamber tracker of the MPD experiment at ...
Added: July 12, 2021
Maksim Golyadkin, Makarov I., , in: Analysis of Images, Social Networks and Texts: 9th International Conference, AIST 2020, Skolkovo, Moscow, Russia, October 15–16, 2020, Revised Selected PapersVol. 12602.: Springer, 2021. P. 230–242.
Manga colorization is time-consuming and hard to automate. In this paper, we propose a conditional adversarial deep learning approach for semi-automatic manga images colorization. The system directly maps a tuple of grayscale manga page image and sparse color hint constructed by the user to an output colorization. High-quality colorization can be obtained in a fully ...
Added: April 9, 2021
Lomov I., Lyubimov M., Makarov I. et al., Journal of Industrial Information Integration 2021 Vol. 23 Article 100216
Automated early process fault detection and prediction remains a challenging problem in industrial processes. Traditionally it has been done by multivariate statistical analysis of sensor readings and, more recently, with the help of machine learning methods. The quality of machine learning models strongly depends on feature engineering, that in turn heavily relies on expertise of ...
Added: March 21, 2021
Alanov A., Kochurov M., Volkhonskiy D. et al., , in: Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP 2020)Vol. 4.: SciTePress, 2020. P. 214–221.
We propose a novel multi-texture synthesis model based on generative adversarial networks (GANs) with a user-controllable mechanism. The user control ability allows to explicitly specify the texture which should be generated by the model. This property follows from using an encoder part which learns a latent representation for each texture from the dataset. To ensure ...
Added: November 8, 2020
A Maevskiy, D Derkach, N Kazeev et al., Journal of Physics: Conference Series 2020 Vol. 1525 No. 012097 P. 1–6
The increasing luminosities of future Large Hadron Collider runs and next generation of collider experiments will require an unprecedented amount of simulated events to be produced. Such large scale productions are extremely demanding in terms of computing resources. Thus new approaches to event generation and simulation of detector responses are needed. In LHCb, the accurate ...
Added: July 27, 2020
Struminsky K., Vetrov D., Lecture Notes in Computer Science 2019 Vol. 11832 P. 81–93
Theoretical analysis in [1] suggested that adversarially trained generative models are naturally inclined to learn distribution with low support. In particular, this effect is caused by the limited capacity of the discriminator network. To verify this claim, [2] proposed a statistical test based on the birthday paradox that partially confirmed the analysis. In this paper, ...
Added: April 23, 2020
Soboleva Natalia, Yakovlev K., , in: Proceedings of the 42nd German Conference on Artificial Intelligence (KI 2019), Kassel, Germany, September 23-26, 2019.: Springer, 2019. P. 316–324.
2D path planning in static environment is a well-known problem and one of the common ways to solve it is to (1) represent the environment as a grid and (2) perform a heuristic search for a path on it. At the same time 2D grid resembles much a digital image, thus an appealing idea comes ...
Added: February 3, 2020
Ildar Lomov, Makarov I., , in: Proceedings of 2nd International Conference on Computer Applications & Information Security (ICCAIS).: NY: IEEE, 2019. P. 1–6.
The progress of deep learning models in image and video processing leads to new artificial intelligence applications in Fashion industry. We consider the application of Generative Adversarial Networks and Neural Style Transfer for Digital Fashion presented as Virtual fashion for trying new clothes. Our model generate humans in clothes with respect to different fashion preferences, ...
Added: July 29, 2019
Kazeev N., Derkach D., Ratnikov F. et al., Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment 2019
Added: July 11, 2019
Derkach D., Kazeev N., Ratnikov F. et al., Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment 2020 Vol. 952 No. 0168-9002 P. 161804
We propose a way to simulate Cherenkov detector response using a generative adversarial neural network to bypass low-level details. This network is trained to reproduce high level features of the simulated detector events based on input observables of incident particles. This allows the dramatic increase of simulation speed. We demonstrate that this approach provides simulation ...
Added: February 11, 2019
Zobnin A., , in: Analysis of Images, Social Networks and Texts. 6th International Conference, 2017, Revised Selected PapersVol. 10716.: Cham: Springer, 2018. Ch. 11 P. 116–128.
Consider a continuous word embedding model. Usually, the cosines between word vectors are used as a measure of similarity of words. These cosines do not change under orthogonal transformations of the embedding space. We demonstrate that, using some canonical orthogonal transformations from SVD, it is possible both to increase the meaning of some components and ...
Added: November 26, 2017