?
Verification of linguistic hypotheses applying large language models
Вестник Череповецкого государственного университета. 2025. Vol. 124. No. 1. P. 80–90.
Victoria I. Firsanova
The paper proposes a novel approach to the verification of linguistic hypotheses applying large language models. The method uses a formal description of a linguistic theory to be proven to build a vector representation for a collection of language data. The representation is compared with embeddings constructed with help of neural network models. The research purpose is to develop a universal tool for the fundamental linguistics by means of language modeling and generative artificial intelligence.
Добрина Д. Н., Nesterenko A., Прикладная дискретная математика. Приложение 2026 № 19 С. 151–159
Работа содержит результаты формального анализа криптографических механизмов, входящих в состав проекта методических рекомендаций «Защищенный универсальный протокол передачи данных и управления микросхемой интеллектуальной карты» (протокол SECUNDA). Получена формальная модель и перечень трудноразрешимых математических задач, трудоёмкостью решения которых можно оценить стойкость используемых криптографических механизмов. ...
Added: September 24, 2026
I.I. Sergeev, I.A. Lomazova, Modeling and Analysis of Information Systems 2026 Vol. 33 No. 3 P. 394–419
Object-centric process mining has emerged as a powerful paradigm for analyzing event data involving multiple interacting business objects. Existing discovery techniques often rely on object-centric Petri nets with fixed arc multiplicities, limiting their ability to represent parametric resource consumption and production patterns and to capture quantitative dependencies between interacting object types. In this paper, we ...
Added: September 24, 2026
Festa G., D'Amato A., Palladino R. et al., European Journal of Innovation Management 2026 Vol. 29 No. 3 P. 728–744
Purpose
Artificial intelligence (AI) is vastly impacting the digital transformation of societies, economies, businesses, markets and enterprises, at a very fast pace, mostly after the global success of the generative algorithms. In this respect, this study, with an exploratory intention, aims to provide evidence about the fundamental issues of AI, particularly if generative, when adapted to ...
Added: September 24, 2026
Alexandrov D., Vasilevsky V., Rezunik L. et al., В кн.: Труды Института системного программирования РАНТ. 38. Вып. 5.: ИСП РАН, 2026. С. 73–90.
Ограничения при выполнении задач, требующих точного извлечения информации из сверхдлинных последовательностей, приводят к снижению качества генерации и отладки кода крупных объектно-ориентированных систем, характеризующихся сложными межклассовыми зависимостями и необходимостью анализа длинных трассировок выполнения, превышающих размеры стандартных контекстных окон. Предлагается технология JavaCapsule для генерации и отладки Java-кода, реализующая итеративную отладку на основе структурированной обратной связи, включающей результаты ...
Added: September 24, 2026
Ivan Bulychev, Savchenko A., AI 2026 Vol. 7 No. 9 Article 380
Recent advances in large language model (LLM) agents have shown promise for autonomous decision-making in recommender systems. However, existing approaches suffer from two fundamental limitations: flat agent memories that conflate different information modalities and prohibitive computational costs that prevent scaling beyond a few hundred users. We propose Hybrid-GraphRAG, a recommender system that integrates hierarchical agent ...
Added: September 24, 2026
Snegirev A., Sychev S., Futures 2026 Vol. 183 P. 1–22
This study addresses the systemic identification and categorization of risks associated with AI development, arising from tensions between technological evolution and institutional, infrastructural, and economic contexts. Drawing on a constructionist methodology, we interpret technological risks as constitutive elements of expert communities' images of the future. Through in-depth interviews with 100 AI experts, proportionally representing corporate, ...
Added: September 23, 2026
Parshakov P., Paklina S., International Journal of Human-Computer Interaction 2026 P. 1–17
This study examines how emotional tone shapes user preference in human–large language model (LLM) interaction. Drawing on the Computers as Social Actors framework, we treat conversational AI as a social communicator whose affective cues influence user judgments. Using large-scale pairwise preference data from LMSYS Chatbot Arena, we model emotional tone through the Valence–Arousal–Dominance framework and ...
Added: September 23, 2026
Andrabi U., Wadood E., Ojha S. K. et al., IEEE Access 2026 Vol. 14 P. 103358–103375
The emergence of 5G networks, aimed at accommodating diverse service requirements such as enhanced Mobile Broadband (eMBB), Ultra-Reliable Low-Latency Communication (URLLC), and massive Machine-Type Communication (mMTC), has presented significant challenges in radio resource management and network slicing. In dynamic heterogeneous network systems, traditional heuristics and mathematical programming methods find it challenging to attain scalable multi-objective ...
Added: September 23, 2026
Paklina S., Parshakov P., Elena Rapoport, Scientometrics 2026 P. 1–26
Generative artificial intelligence has become a routine part of academic writing. While much of the debate has focused on questions of integrity and authorship, less attention has been paid to how AI-assisted writing may affect research evaluation itself. This paper asks a straightforward but important question: does the use of LLMs in academic writing change ...
Added: September 23, 2026
Кузнецова М. П., Klochko O., Современная мировая экономика 2026 Т. 4 № 2 С. 6–25
The article examines the positions of the world’s largest countries in the industrial robotics sector as one of the key areas for the physical artificial intelligence (AI). The aim of the study is to conduct a comparative assessment of the readiness of leading economies to develop physical AI based on an analysis of production, foreign ...
Added: September 23, 2026
Kertesz-Farkas A., Acquaye F. L., Journal of Proteome Research 2026 Vol. 25 P. 3764–3768
Ultimately, most tandem mass spectrometry (MS/MS) proteomics experiments aim to not just detect but also quantify the proteins in a given complex sample. Here, we describe an extension to the Crux MS/MS analysis toolkit to enable label-free quantification of peptides. We demonstrate that Crux’s new quantification command, which is modeled after the algorithms implemented in ...
Added: September 23, 2026
Maddalena L., Yildiz B., Del Vecchio Blanco F. et al., Risk Analysis 2026 Vol. 46 No. 4 P. 1–26
Heated tobacco products (HTPs) are marketed as alternatives to conventional cigarettes with a potential reduced risk profile. Yet, their actual impact on cancer and noncancer disease risk remains uncertain and requires rigorous quantitative assessment. In this study, we develop a unified and transparent computational framework for toxicological risk assessment of HTPs, integrating chemical emissions data ...
Added: September 22, 2026
Ulyanina O. A., Vikhrova E. N., RUDN Journal of Psychology and Pedagogics 2025 Vol. 22 No. 2 P. 337–360
Rapid digitalization of higher education and the rise of artificial intelligence (AI) in instruction call for careful evaluation of their impact on students. Traditional face-to-face lectures and those given by an AI-avatar, remote online courses, each create distinct conditions that shape the classroom psychological climate and comfort. Prior research shows AI integration increases engagement, but ...
Added: September 21, 2026
Aleksei Samarin, Alexander Savelev, Aleksei Toropov et al., Pattern Recognition and Image Analysis 2024 Vol. 34 No. 3 P. 855–862
Tasks related to the automation of medical data processing are becoming more urgent. Particular attention is paid to systems for monitoring and analyzing human physiological parameters. Such systems often use specialized sensors to capture biomedical images, such as infrared cameras. This article describes our study of the problem of segmenting the eye pupil and iris ...
Added: September 21, 2026
Aleksei Samarin, Nazarenko A., Alexander Savelev et al., Pattern Recognition and Image Analysis 2024 Vol. 34 No. 3 P. 844–854
Improving image quality is becoming an increasingly popular task, especially when working with mobile devices. One common approach to image enhancement is the use of convolutional neural networks. However, to achieve good results, such networks must be large enough, otherwise there is a risk of unwanted artifacts. In addition, large convolutional neural networks require significant ...
Added: September 21, 2026
Aleksei Samarin, Alexander Savelev, Aleksei Toropov et al., Optical Memory and Neural Networks (Information Optics) 2024 Vol. 33 P. 424–434
This study explores the development of classifiers for microbial images, specifically focusing on streptococci captured via microscopy of live samples. Our approach uses AutoML-based techniques and automates the creation and analysis of feature spaces to produce optimal descriptors for classifying these microscopic images. This technique leverages interpretable taxonomic features based on the external geometric attributes ...
Added: September 21, 2026
Aleksei Samarin, Aleksei Toropov, Alexander Savelev et al., Pattern Recognition and Image Analysis 2024 Vol. 34 No. 4 P. 1053–1060
This paper presents a novel approach to classification in biomedical imaging, specifically targeting polyp recognition in video endoscopy snapshots. Our method leverages specialized image descriptors to enhance the accuracy and robustness of polyp recognition. By employing these specialized descriptors, we address the challenges inherent in analyzing biomedical images from open datasets. Our approach not only ...
Added: September 21, 2026
Самарин А. В., Торопов А. Г., Савельев А. Г. et al., Pattern Recognition and Image Analysis 2024 Vol. 34 No. 4 P. 1044–1052
This paper presents a study aimed at improving the detection quality of small-sized microorganisms under challenging microscopic conditions through the application of a lightweight combined image preprocessing model. We focused on the task of detecting diplococci in images obtained through dynamic sample microscopy. The proposed approach employs predefined filters for image preprocessing, combined with the ...
Added: September 21, 2026
Singapore: Springer, 2025.
Added: September 21, 2026
Tomat A., Sergei O. Kuznetsov, International Journal of Approximate Reasoning 2026 Vol. 197 Article 109754
Interval Pattern Structures (IPS) provide a natural way to represent local, human-readable explanations for predictions on numerical data through vectors of intervals interpreted as axis-parallel hyper-rectangles. In this paper, we develop and evaluate an IPS-based k-nearest neighbors classifier, IPS-KNN, that explains each prediction through a single local interval description rather than through the aggregation of ...
Added: September 21, 2026
Aleksei Samarin, Nazarenko A., Kotenko E. et al., / Series arXiv "math". 2025. No. 2511.20141.
This paper presents a novel approach to neural network compression that addresses redundancy at both the filter and architectural levels through a unified framework grounded in information flow analysis. Building on the concept of tensor flow divergence, which quantifies how information is transformed across network layers, we develop a two-stage optimization process. The first stage ...
Added: September 21, 2026
Aleksei Samarin, Alexander Savelev, Aleksei Toropov et al., Pattern Recognition and Image Analysis 2025 Vol. 35 No. 2 P. 169–178
This study explores the incorporation of specialized self-attention mechanisms into deep learning architectures, with a particular emphasis on segmenting human iris and pupil regions in infrared images. In this work, we present some modified versions of nonlocal blocks designed to enhance self-attentive properties while addressing the distinct characteristics of infrared imaging data. By applying these customized ...
Added: September 21, 2026
Aleksei Samarin, Alexander Savelev, Aleksei Toropov et al., Journal of Imaging 2025 Vol. 11 No. 10 Article 359
Timely identification and accurate delineation of ultra-early ischemic stroke lesions in non-contrast computed tomography (CT) scans of the human brain are of paramount importance for prompt medical intervention and improved patient outcomes. In this study, we propose a deep learning-driven methodology specifically designed for segmenting ultra-early ischemic regions, with a particular emphasis on both the ...
Added: September 21, 2026
Шиповалова Л. В., Социология власти 2026 Vol. 38 No. 1 P. 224–243
This article examines the integration of large language model based chatbots into educational practices in Russian higher education through the lens of critical theory and curriculum ideologies. Drawing on Ivan Illich’s concept of convivial tools and Jürgen Habermas’s distinction between instrumental and communicative rationality, the authors conceptualize large language models as technologies capable of operating ...
Added: September 18, 2026