Large language models (LLMs) are increasingly being used for code generation. However, both the generated code and the underlying LLM-based systems demand rigorous security evaluation. A common approach to enhancing code generation quality involves multi-agent systems composed of multiple models. This paper evaluates the performance of GPT-OSS 20B, GPT-OSS 120B, and Qwen3-Coder 480B models in single-agent and multi-agent configurations, using two code security benchmarks, SecurityEval and CyberSecEval. The key contribution is SafeAICoder, an extensible and scalable framework for testing LLMs enabling distributed server-side generation of multi-module programs and tests, independent of client-side code.
This study is dedicated to experiments in Word Sense Disambiguation on Russian-language material using generative (decoder-only) models of small and medium size. While the direct application of generative models is not an optimal approach for this task, such models demonstrate potential as semantic annotators of large volumes of raw data. The automation of semantic text annotation using generative models may help overcome the bottleneck of insufficient labeled data for training encoder-based models. Previous studies show that state-of-the-art English and multilingual models can achieve accuracy above 90% on this task, while smaller models typically reach 80%+. The present study aims to determine whether a comparable task can be successfully addressed for small- and medium-scale models adapted to Russian, that do not require substantial computational resources. The experiments reported in this paper are conducted both in a basic setting (one/few-shot prompting) with separate tests for narrow and broad context windows of the ambiguous lexeme, as well as under several modifications, such as context enrichment with paradigmatic information (e.g., hypernyms, hyponyms, domain labels of the target word) and ensemble approaches in which one model validates and refines the predictions of another. The study is based on the Russian annotated resource RuSemCor, annotated in terms of the RuWordNet semantic net. The experiments ultimately pursue the development of an efficient and accessible pipeline for automatic semantic annotation of Russian texts, useful both for direct application and for preparing annotated data for machinelearning tasks.
Automating the verification of building information models for compliance with fire safety regulations remains a pressing issue in the architectural and construction industry. Existing automated verification systems rely on rule-based approaches that ignore the building's topological context and are poorly adapted to new projects. This paper examines the development and experimental verification of methods for predicting door fire protection parameters in BIM models using graph neural networks and validating the approach using real-world design data from seven residential buildings provided by a major real estate developer. A methodology for predicting door fire resistance classes based on relational graph convolutional networks is proposed, along with a pipeline for extracting data from a specialized format, constructing a graph, and generating features that take into account geometric, semantic, and topological characteristics. Experiments were conducted to predict the presence and fire resistance class with cross-project validation using the "one building out of sample" principle. The developed approach enables automated verification of fire protection parameters and reduces the time required to analyze building models. The use of graph neural networks ensures that topological context is taken into account and high prediction accuracy is achieved, while the use of real data from a major real estate developer confirms the practical applicability of the method.
The results of research on parallel applications for heterogeneous architectures using the SYCL standards and the DPC++ language, as well as OpenMP, developed by students of the Department of Applied Mathematics and Artificial Intelligence (AM&AI) at MPEI during research work are presented. As an applied problem, the search for shortest paths in graphs of various dimensions using the Bellman–Ford and delta‑step algorithms is considered. The impact of algorithm choice on the solution efficiency, as well as the heterogeneous multi-core architecture, is examined. The Bellman-Ford algorithm is easily parallelized and demonstrated excellent scalability. In contrast, using a GPU for the delta-step algorithm did not provide significant speedup due to the complexity of memory coordination and the need to repeatedly copy data between devices. Testing was conducted using the following hardware: an Intel Core i5-12400F CPU (6 cores, 12 threads) and an NVIDIA GeForce GTX1660 GPU (1408 CUDA cores). The test results show that even within a single computational task, different implementations can exhibit different behavior when the task parameters are changed. This confirms the importance of preliminary analysis and testing when choosing a hardware&software architecture for tasks requiring high performance. The developed software suite visualizes the dependence of parallel algorithm implementation speedup on the number of vertices in the graph for various method parameters and is successfully used in the educational and research processes of the AM&AI Department at MPEI.
The work is a pioneer in studying of the chemical composition at the micro-impurity level of archaeological copper coins as an information basis for identifying the features of monetary circulation in the medieval state. An interdisciplinary study of the numismatic material from the Bulgarian settlement of 98 copper coins, represented by 91 Golden Horde, 6 foreign coins of the same period and one coin of the pre-Mongol period of the Zengid dynasty, was conducted. The article contains attribution with images of the obverse and reverse of coins and data of archaeometric chemical composition study of monetary artifacts using two independent methods – X-ray fluorescence and emission spectral. This is the first interdisciplinary study in our country at present time, covering a representative collection of copper coins of various rulers and mints from archaeological materials of the Bulgarian settlement. As a result of studying the chemical composition of the coins, the ratios of impurities in copper alloys were determined, which divide the collection into ten main groups, including coins of various minted courts and rulers of a certain date. The determination of the impurity composition allows not only to classify coins into groups, but also to put forward reasonable hypotheses about the geographical location of copper deposits used for minting. The database, compiled from the research results and combining numismatic attribution, coin images, and chemical composition data, is published as an open dataset in the Zenodo repository and is intended for the application of machine learning and artificial intelligence methods in the tasks of automatic identification and provenance analysis of medieval coins.
