?
Proceedings of the AAAI Conference on Artificial Intelligence. AAAI-26: AAAI Technical Track on Planning, Routing, and Scheduling; AAAI Technical Track on Reasoning under Uncertainty; AAAI Technical Track on Search and Optimization. Main Track, volume 40 no. 43
We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.
The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-26 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.
Chapters
Savchenko A., Kachan O., , in: Proceedings of the AAAI Conference on Artificial Intelligence. AAAI-26: AAAI Technical Track on Planning, Routing, and Scheduling; AAAI Technical Track on Reasoning under Uncertainty; AAAI Technical Track on Search and Optimization. Main Track, volume 40 no. 43.: American Association for Artificial Intelligence (AAAI) Press, 2026.
Accurate forecasting of multivariate time series data remains a formidable challenge, particularly due to the growing complexity of temporal dependencies in real-world scenarios. While neural network-based models have achieved notable success in this domain, complex channel-dependent models often suffer from performance degradation compared to channel-independent models that do not consider the relationship between components but ...
Added: January 21, 2026
Bogdan Butyrin, Artemy Rubtsov, Naumov A. et al., , in: Proceedings of the AAAI Conference on Artificial Intelligence. AAAI-26: AAAI Technical Track on Planning, Routing, and Scheduling; AAAI Technical Track on Reasoning under Uncertainty; AAAI Technical Track on Search and Optimization. Main Track, volume 40 no. 43.: American Association for Artificial Intelligence (AAAI) Press, 2026. P. 36627–36635.
In this paper, we establish non-asymptotic bounds for accuracy of normal approximation for linear two-timescale stochastic approximation (TTSA) algorithms driven by martingale difference or Markov noise. Focusing on both the last iterate and Polyak–Ruppert averaging regimes, we derive bounds for normal approximation in terms of the convex distance between probability distributions. Our analysis reveals a ...
Added: January 26, 2026
Levin I., Naumov A., Samsonov S., , in: Proceedings of the AAAI Conference on Artificial Intelligence. AAAI-26: AAAI Technical Track on Planning, Routing, and Scheduling; AAAI Technical Track on Reasoning under Uncertainty; AAAI Technical Track on Search and Optimization. Main Track, volume 40 no. 43.: American Association for Artificial Intelligence (AAAI) Press, 2026. P. 36696–36704.
In this paper, we study the bias and high-order error bounds of the Linear Stochastic Approximation (LSA) algorithm with Polyak-Ruppert (PR) averaging under Markovian noise. We focus on the version of the algorithm with constant step size and propose a novel decomposition of the bias via a linearization technique. We analyze the structure of the ...
Added: April 17, 2026
Tsyganov A., Frolov E., Samsonov S. et al., , in: Proceedings of the AAAI Conference on Artificial Intelligence. AAAI-26: AAAI Technical Track on Planning, Routing, and Scheduling; AAAI Technical Track on Reasoning under Uncertainty; AAAI Technical Track on Search and Optimization. Main Track, volume 40 no. 43.: American Association for Artificial Intelligence (AAAI) Press, 2026. P. 26010–26018.
In this paper, we propose new randomized algorithms for estimating the two-to-infinity and one-to-two norms in a matrixfree setting, using only matrix-vector multiplications. Our methods are based on appropriate modifications of Hutchinson’s diagonal estimator and its Hutch++ version. We provide oracle complexity bounds for both modifications. We further illustrate the practical utility of our algorithms ...
Added: January 26, 2026
Soboleva V., Alanov A., Kuznetsov A. et al., , in: Proceedings of the AAAI Conference on Artificial Intelligence. AAAI-26: AAAI Technical Track on Planning, Routing, and Scheduling; AAAI Technical Track on Reasoning under Uncertainty; AAAI Technical Track on Search and Optimization. Main Track, volume 40 no. 43.: American Association for Artificial Intelligence (AAAI) Press, 2026. Ch. 11 P. 9051 – 9059.
While diffusion model fine-tuning offers a powerful approach for customizing pre-trained models to generate specific objects, it frequently suffers from overfitting when training samples are limited, compromising both generalization capability and output diversity. This paper tackles the challenging yet most impactful task of adapting a diffusion model using just a single concept image, as single-image ...
Added: June 1, 2026
Karpukhin I., Savchenko A., , in: Proceedings of the AAAI Conference on Artificial Intelligence. AAAI-26: AAAI Technical Track on Planning, Routing, and Scheduling; AAAI Technical Track on Reasoning under Uncertainty; AAAI Technical Track on Search and Optimization. Main Track, volume 40 no. 43.: American Association for Artificial Intelligence (AAAI) Press, 2026. P. 22536–22544.
Long-horizon events forecasting is a crucial task across various domains, including retail, finance, healthcare, and social networks. Traditional models for event sequences often extend to forecasting on a horizon using an autoregressive (recursive) multi-step strategy, which has limited effectiveness due to typical convergence to constant or repetitive outputs. To address this limitation, we introduce DEF, a novel approach for simultaneous forecasting of ...
Added: June 17, 2026
Research target:
Computer Science
Language:
English
Keywords: artificial intelligence
Myachin A. L., Procedia Computer Science 2026 Vol. 287 P. 193–200
We extend the static pattern analysis method to the temporal dimension by introducing a six-type trajectory taxonomy that classifies objects according to the frequency and structure of pattern switches over an observation window of T > 8 periods. For each object, a reference pattern is designated as the most frequently occupied group over the observation ...
Added: September 18, 2026
Obukhov K., Раведовская У. Ю., Высшее образование в России 2026 Т. 35 № 1 С. 77–95
The article focuses on the strategies that Russian university lecturers use to maintain their professional status amid the active implementation of artificial intelligence technologies, specifically large language models. The objective is to identify and reconstruct the key strategies of symbolic defense and repositioning of the higher education teaching profession in the context of Russian higher ...
Added: September 18, 2026
Громов Р. С., Нестеров Р.А., Proceedings of the Institute for System Programming of the RAS 2026 Vol. 38 No. 4 P. 23–44
This paper explores the performance criteria of the newest algorithm for solving the problem of finding shortest paths on a graph from a given vertex – Bounded Multi-Source Shortest Path Algorithm
(BM-SSP). The algorithm was published in 2025 and, as its creators claim, it is asymptotically superior to Dijkstra’s deterministic algorithm. However, in the publication devoted ...
Added: September 18, 2026
Моисеев Г. В., Гуманитарные исследования в Восточной Сибири и на Дальнем Востоке 2026 № 2 (76) С. 58–68
The article presents a philosophical analysis of the transformation of labor in the context of the spread of AI technologies. Criticizing the notion of AI as an autonomous and neutral technology leading to the replacement of human labor, the author proposes to analyze the social consequences of AI development within the framework of automation processes ...
Added: September 17, 2026
Кузнецов М. Е., Полякова М., Лукьянович В. et al., ФАНУ "Востокгосплан", 2026.
Обзор международных практик развития робототехники и искусственного интеллекта и оценка возможностей их применения в условиях России, в первую очередь для Дальнего Востока и Арктической зоны РФ ...
Added: September 16, 2026
Melman A., Evsyutin O., Computer Science Review 2027 Vol. 63 (A) Article 101066
One of the effective means of protecting digital images is invisible watermarking. Different scenarios have different requirements for watermark resistance to post-processing. Robust watermarking schemes are resistant to a wide range of modifications. Fragile watermarking schemes are designed for integrity control and are destroyed by even minor modifications of images. Semi-fragile watermarking schemes combine features ...
Added: September 15, 2026
Воронова К. Д., Lyadova L. N., Proceedings of the Institute for System Programming of the RAS 2026 Vol. 38 No. 4 P. 153–170
Title: Automated Event Logs Generation Based on Unstructured Internet Sources for Process Analysis Tasks
Abstract. This paper presents an approach to automated structuring event-related information extracted from unstructured textual Internet sources for process mining tasks. In many practical cases, information on events associated with various processes is not presented in the form of ready-made event logs, but is ...
Added: September 14, 2026
Springer, 2026.
This book gathers selected papers from the KES-IDT 2025 conference, held in Solin, Croatia, on June 25–27, 2025. The book presents and discusses the latest research results and generates new ideas in the field of intelligent decision-making. The range of topics discussed is classification, prediction, data analysis, big data, data science, decision support, knowledge engineering, ...
Added: September 13, 2026
Lebedev O. B., Митяков Е. С., Саенко И. Б. et al., Информация и космос 2026 № 1 С. 53–58
The article presents a methodology for the integrated assessment of cyberattacks on industrial control systems (ICS) using a combination of the Ampire cyber range and a digital twin. The approach is based on calculating five criteria—severity, attacker capabilities, vulnerability, complexity, and defense effectiveness—that form an integrated threat index. Testing across three scenarios confirmed the index's ...
Added: September 13, 2026
Lebedev O. B., Лебедев Б. К., Бесхмельнов М. И., Известия ЮФУ. Технические науки 2024 № 2(242) С. 177–190
This article examines algorithms for generating motion trajectories for unmanned aerial vehicles (UAVs) during search-and-rescue and emergency response operations. It describes methods and algorithms for controlling the movement of a UAV group in various formations—such as line, rank, column, and during turns. Control is achieved through alternative collective adaptation algorithms based on principles of collective ...
Added: September 13, 2026
Lebedev O. B., Котов Д. В., Известия ЮФУ. Технические науки 2024 № 1(237) С. 155–167
The primary approach to solving motion planning and control problems involves the use of intelligent technologies. These technologies are applied to define and adjust control objectives and action programs, as well as to formulate control algorithms under conditions of uncertainty—stemming from various factors—across actuator elements and the motion control, planning, and behavioral subsystems. This paper ...
Added: September 13, 2026
Гибридный алгоритм оптимизации на основе объединения моделей роевого интеллекта: роя хромосом и пчел
Lebedev O. B., Лебедев Б. К., Ганжур М. А., Информатизация и связь 2023 № 2 С. 80–84
A hybrid algorithm has been developed to solve the VLSI component placement problem by combining procedures based on bee colony behavior and a chromosome swarm. The optimization criterion is based on estimates of the number of nets crossing specific lines within the routing area. A modified chromosome swarm paradigm is described; unlike the canonical method, ...
Added: September 13, 2026
Lebedev O. B., Лебедев Б. К., Бесхмельнов М. И., Вестник Тверского государственного технического университета 2025 № 3(27) С. 103–119
The article presents a detailed analysis of a hybrid path-planning algorithm designed for navigation in a two-dimensional space, accounting for partial uncertainty regarding terrain information. The algorithm operates in stages and is divided into two levels. At the first level, the object's local visibility zone is established, and the corresponding region on the map is ...
Added: September 12, 2026
Lebedev O. B., Лебедев Б. К., Бесхмельнов М. И., Известия ЮФУ. Технические науки 2025 Т. 2(244) С. 68–82
This paper describes a hybrid situational trajectory planning algorithm for 2D space operating under conditions of partial uncertainty. Based on the integration of wave-propagation and ant colony optimization algorithms, it enables the real-time generation of minimum-length trajectories while simultaneously optimizing other path quality criteria. The processes of generating a trajectory segment and moving the object ...
Added: September 12, 2026
Lebedev O. B., Beskhielnov M. I., OPTIMIZATION BY THE SWARM OF TRANSFORMING CHROMOSOMES METHOD 2024 Vol. 34 No. 3 P. 652–658
A new strategy for finding effective solutions based on modification and hybridization of the canonical representations of the particle swarm algorithm is proposed. A paradigm of a swarm of transforming chromosomes is described, making it possible to represent solutions in the affine space of chromosomes with integer parameter values. The mechanisms of chromosome transformation in ...
Added: September 12, 2026
Lebedev O. B., Левченко Д. Д., Черкасов Р. И., Инженерный вестник Дона 2026 № 2(134) Статья 7
This article analyzes the impact of artificial intelligence (AI) and machine learning technologies on the development and transformation of cyberthreats and the creation of highly effective cyberdefense systems. Key trends in AI evolution are discussed, including data-, model-, application-, and human-centric approaches, and their role in shaping both defensive and offensive capabilities. It is shown ...
Added: September 12, 2026
Marinin N., Getman A., Труды Института системного программирования РАН 2026 Т. 38 № 4 С. 123–142
This paper investigates a method for detecting DNS tunnels in network traffic using a neural network.
To achieve this, an analysis of current detection approaches was conducted, and a dataset for neural network
training was prepared. The proposed model takes as input a sequence of characters extracted from DNS
responses. The trained model demonstrated an F1-score close to ...
Added: September 11, 2026
Савченко В. В., Savchenko L., Измерительная техника 2026 Т. 75 № 3 С. 105–113
Within the framework of a current area of research in the field of speech acoustics – non-invasive analysis of speech
production processes – the acute problem of insufficient accuracy of parametric methods for coding a turbulent (noise) type voice source is considered. In order to overcome this problem, a method for coding a sound source with increased ...
Added: September 11, 2026
Филатова А. А., Эпистемология и философия науки 2026 Т. 63 № 2 С. 154–171
intelligence (hereafter, AI), particularly in the form of large lan guage models, has prompted a renewed wave of philosophical debates concerning the semantic competences of technical sys tems and the criteria for evaluating the outputs they generate, especially textual outputs. This article examines a set of central problem areas and their treatment in contemporary philosophical ...
Added: September 10, 2026
Lebedev O. B., Черкасов Р. И., Известия ЮФУ. Технические науки 2025 № 5(247) С. 254–276
This paper considers the application of artificial intelligence technologies, in particular computer vision, in visual information processing systems. A comprehensive analysis of neural network approaches to solving computer vision problems is carried out, including systematization of key types of problems: image classification, object detection and semantic segmentation. The architectural principles of convolutional neural networks are ...
Added: September 10, 2026
Lebedev O. B., Beskhmelnov M. I., PATTERN RECOGNITION AND IMAGE ANALYSIS. ADVANCES IN MATHEMATICAL THEORY AND APPLICATIONS 2024 Vol. 34 No. 3 P. 543–548
The work describes a hybrid algorithm for the dynamic formation of a robot’s movement route in nondeterministic environments with bypassing stationary and nonstationary obstacles for two-dimensional space, based on the integration of wave and ant algorithms, which makes it possible to build trajectories of minimum length in real time with simultaneous optimization of a number ...
Added: September 10, 2026
Lebedev O. B., Лебедев Б. К., Известия ЮФУ. Технические науки 2026 № 2(250) С. 151–173
This paper proposes a methodology and method for constructing a model of the study area as a finite set of zones (sections) covering it, characterized by the fact that all sections are rectangular. The paper examines methods for forming a minimal set of sections on a large field that completely cover the accessible territory surveyed ...
Added: September 10, 2026
Lebedev O. B., Шмелева А. Г., Гежа Н. С., Информатика и автоматизация (Труды СПИИРАН) 2026 Т. 25 № 3 С. 720–750
This paper describes the development of a neural network model for automated analysis of medical data in electrophysiology based on deep learning methods. The relevance of this work stems from the growing need to improve the objectivity, speed, and accuracy of processing complex spatiotemporal signals, such as ECG or EEG. Convolutional neural networks (CNNs), which ...
Added: September 10, 2026
V. Firsanova, Journal of Mathematical Sciences 2024 Vol. 285 P. 112–125
Text-to-image models use user-generated prompts to produce images. Such text-to-image models as DALL-E 2, Imagen, Stable Diffusion, and Midjourney can generate photorealistic or similar to human-drawn images. Apart from imitating human art, large text-to-image models have learned to produce combinations of pixels reminiscent of captions in natural languages. For example, a generated image might contain ...
Added: September 9, 2026