Volume 267: International Conference on Machine Learning, 13-19 July 2025, Vancouver Convention Center, Vancouver, Canada. Val. 267.

?

Volume 267: International Conference on Machine Learning, 13-19 July 2025, Vancouver Convention Center, Vancouver, Canada

Vol. 267. 2025.

Under the general editorship: A. Singh, M. Fazel, D. Hsu, S. Lacoste-Julien, F. Berkenkamp, T. Maharaj, K. Wagstaff, J. Zhu

Inverse Bridge Matching Distillation

Gushchin N., Li D., Daniil Selikhanovych et al., , in: Volume 267: International Conference on Machine Learning, 13-19 July 2025, Vancouver Convention Center, Vancouver, CanadaVol. 267.: [б.и.], 2025. P. 21471–21496.

Learning diffusion bridge models is easy; making them fast and practical is an art. Diffusion bridge models (DBMs) are a promising extension of diffusion models for applications in image-to-image translation. However, like many modern diffusion and flow models, DBMs suffer from the problem of slow inference. To address it, we propose a novel distillation technique ...

Added: November 6, 2025

GLGENN: A Novel Parameter-Light Equivariant Neural Networks Architecture Based on Clifford Geometric Algebras

Filimoshina E., Shirokov D., , in: Volume 267: International Conference on Machine Learning, 13-19 July 2025, Vancouver Convention Center, Vancouver, CanadaVol. 267.: [б.и.], 2025. P. 17153–17188.

We propose, implement, and compare with competitors a new architecture of equivariant neural networks based on geometric (Clifford) algebras: Generalized Lipschitz Group Equivariant Neural Networks (GLGENN). These networks are equivariant to all pseudo-orthogonal transformations, including rotations and reflections, of a vector space with any non-degenerate or degenerate symmetric bilinear form. We propose a weight-sharing parametrization ...

Added: October 28, 2025

Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models

Alina Shutova, Vladimir Malinovskii, Vage Egiazarian et al., , in: Volume 267: International Conference on Machine Learning, 13-19 July 2025, Vancouver Convention Center, Vancouver, CanadaVol. 267.: [б.и.], 2025.

Efficient real-world deployments of large language models (LLMs) rely on Key-Value (KV) caching for processing and generating long outputs, reducing the need for repetitive computation. For large contexts, Key-Value caches can take up tens of gigabytes of device memory, as they store vector representations for each token and layer. Recent work has shown that the ...

Added: November 6, 2025

On Linear Convergence in Smooth Convex-Concave Bilinearly-Coupled Saddle-Point Optimization: Lower Bounds and Optimal Algorithms

Borodich E., Gasnikov A., Kovalev D., , in: Volume 267: International Conference on Machine Learning, 13-19 July 2025, Vancouver Convention Center, Vancouver, CanadaVol. 267.: [б.и.], 2025. P. 5045–5100.

Added: November 18, 2025

FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training

Zmushko P., Beznosikov A., Takáč M. et al., , in: Volume 267: International Conference on Machine Learning, 13-19 July 2025, Vancouver Convention Center, Vancouver, CanadaVol. 267.: [б.и.], 2025. P. 80708–80739.

With the increase in the number of parameters in large language models, the training process increasingly demands larger volumes of GPU memory. A significant portion of this memory is typically consumed by the optimizer state. To overcome this challenge, recent approaches such as low-rank adaptation (LoRA), low-rank gradient projection (GaLore), and blockwise optimization (BAdam) have ...

Added: November 10, 2025

Revisiting Non-Acyclic GFlowNets in Discrete Environments

Morozov N., Maximov I., Tiapkin D. et al., , in: Volume 267: International Conference on Machine Learning, 13-19 July 2025, Vancouver Convention Center, Vancouver, CanadaVol. 267.: [б.и.], 2025. P. 44887–44910.

Generative Flow Networks (GFlowNets) are a family of generative models that learn to sample objects from a given probability distribution, potentially known up to a normalizing constant. Instead of working in the object space, GFlowNets proceed by sampling trajectories in an appropriately constructed directed acyclic graph environment, greatly relying on the acyclicity of the graph. ...

Added: October 15, 2025

Research target: Computer Science

Language: English

Text on another site

Keywords: Machine Learning

Publication based on the results of:

Development of theoretical foundations and methods of generative artificial intelligence and their application to heterogeneous domain area (2025)

Volume 267: International Conference on Machine Learning, 13-19 July 2025, Vancouver Convention Center, Vancouver, Canada

Proceedings of the 9th Student Research Workshop associated with the International Conference Recent Advances in Natural Language Processing

Velichkov B., Nikolova-Koleva I., Slavcheva M., INCOMA Ltd, 2025.

The RANLP 2025 Student Research Workshop (RANLPStud’2025) is a special track of the established international conference Recent Advances in Natural Language Processing (RANLP’2025). The RANLPStud is being organised for the 9th time and this year is running in parallel with the other tracks of the main RANLP 2025 conference. The target of RANLPStud’25 is to be a ...

Added: May 12, 2026

Интегрированная среда моделирования для верификации и валидации программ управления подключенными и высокоавтоматизированными транспортными средствами

Stepanyants V., Долгов И. М., Хорошилов Г. С. et al., Труды Института системного программирования РАН 2026 Т. 38 № 3 С. 95–110

Highly automated and connected vehicles are gradually entering the market. Currently, solutions are being proposed that allow these technologies to be used for cooperative driving automation, which can significantly improve traffic safety. Such technologies and their software should be tested to ensure safety before being implemented in real systems. Verification and validation of vehicular control ...

Added: May 12, 2026

Connected and Automated Vehicle Scenario Manager Graphical User Interface

Tikhonov R., Efendiev M. T., Fedotenkov A. A., 2026 International Russian Smart Industry Conference (SmartIndustryCon) 2026 P. 542–547

High-fidelity simulation environments like CARLA and ROS are essential for connected and automated vehicle research. They allow researchers to verify and validate new software and technology without the time, financial, and safety overheads of real-world testing. However, their operation requires considerable expertise for creating platform-specific scenario configuration files, which complicates the research workflow. This paper ...

Added: May 11, 2026

Proceedings 2026 IEEE 11th International Conference on Smart Cloud SmartCloud 2026 8-10 May 2026

Los Alamitos: IEEE Computer Society, 2026.

It is a great pleasure for us to welcome you on behalf of the conference committees, to the 11th IEEE International Conference on Smart Cloud (IEEE SmartCloud 2026), we are glad that we can have this international conference in New York city, USA. Now, please allow us to introduce the IEEE SmartCloud 2026 conference. The ...

Added: May 10, 2026

От неизвестности к прозрачности: обзор технологий объяснимого ИИ (XAI)

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

Explainable AI for Industry 5.0: Shedding light on the black box

Avdoshin S. M., Pesotskaya E. Y., Business Informatics 2026 Vol. 20 No. 1 P. 7–28

The rapid development of artificial intelligence (AI) is accompanied by increasing computational complexity and decreasing model transparency, which significantly limits its adoption in critical domains that require a high level of trust, interpretability, and justification of decisions. Under these conditions, the field of Explainable Artificial Intelligence (XAI) has gained particular importance as it focuses on approaches and technologies that ...

Added: May 8, 2026

Comparative Analysis of Students’ Perceptions of Programming Puzzles: Parson’s and Wordle-Like

Varnavsky A., IEEE Access 2026 Vol. 14 P. 37487–37508

Puzzles are an excellent tool for learning computer science and programming, fostering increased interest, engagement, and motivation among students, as well as developing logical, critical, and computational thinking. Among beginner programmers, Parson's Programming Puzzles are quite popular, aimed at mastering the basic syntactic and logical constructs of programming languages. However, as students' skills grow, their ...

Added: May 7, 2026

Towards performance analysis of GPU-aware MPI over Angara interconnect

Ismagilov T., Mukosey A., Smirnov F. et al., International Journal of High Performance Computing Applications 2026 Vol. 40 No. 2 P. 240–253

One of the most important aspects of supercomputer development in the post-Moore era is the interconnect technologies that allow one to unite a multitude of processing elements into a well-synchronized computing system. Novel types of supercomputer interconnect require careful benchmarking and compliance with the requirements of modern hardware trends. GPU-based heterogeneous computing is one of ...

Added: May 7, 2026

Программные инструментальные средства для разработки мероприятий по снижению брака серийного производства

Yasnitsky L., Голдобин М. А., Мезенцев А. С., Прикладная математика и вопросы управления 2025 № 2 С. 99–116

Представлен обзор современных методов и основанных на них программных инструментах, применяемых для математического моделирования серийных производственных процессов с целью снижения брака и повышения качества производимых изделий. Перечисляются группы работ, нацеленных на обнаружение и классификацию дефектов, работ, в которых решаются задачи прогнозирования образования дефектов и определения значимости параметров, работ направленных на поиск оптимального сочетания технологических параметров изготовления изделий, ...

Added: May 5, 2026

Моделирование и оценка ресурсных затрат алгоритмов маршрутизации в сетях на кристалле с двумерной циркулянтной топологией

Монахова Э. А., Монахов О. Г., Rzaev E. et al., Прикладная дискретная математика 2026 Т. 71 С. 112–127

В настоящей работе исследовано совместное конструирование топологий семейств оптимальных по диаметру циркулянтных сетей $C(N; \pm 1, \pm s_2)$ и реализуемых для них оптимальных алгоритмов маршрутизации сложности $O(1)$. Предлагаемый алгоритм маршрутизации основан на использовании масштабируемых параметров $L$-образных шаблонов плотной укладки графов на плоскости для семейств оптимальных сетей. Определены аналитические формулы зависимости этих параметров от диаметра графов семейств ...

Added: May 4, 2026

AlphaDent: A dataset for automated tooth pathology detection

Sosnin E. I., Vasil’ev Y. L., Solovyev R. A. et al., Computer Optics 2025 Vol. 49 No. 6 P. 1129–1137

In this article, we present a new unique dataset for dental research – AlphaDent. This dataset is based on the DSLR camera photographs of the teeth of 295 patients and contains over 1200 images. The dataset is labeled for solving the instance segmentation problem and is divided into 9 classes. The article provides a detailed ...

Added: May 4, 2026

Мультимодальные модели в медицинской диагностике как универсальный инструмент

Назаренко А. Г., Федоров М. В., Moshkin A. et al., Вестник Росздравнадзора 2026 № 1 С. 14–29

Multimodal foundation models and medical multimodal large language models are establishing a new class of diagnostic clinical decision support systems capable of operating on heterogeneous data sources, including medical imaging (X-ray, CT, MRI, ultrasound, histopathology), physiological signals (ECG, EEG), clinical text (electronic health records, reports, discharge summaries), laboratory measurements, molecular profiling data, and related modalities. ...

Added: May 4, 2026

2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)

Honolulu: IEEE, 2025.

International Conference on Computer Vision Workshops (ICCVW), Honolulu, HI, USA, 2025 ...

Added: May 3, 2026

MinMAE calibration method for convolutional neural network quantization

Vasilev A., Kapitanov A., Solovyev Roman A. et al., PeerJ Computer Science 2026 Vol. 12 Article 3724

This article introduces MinMAE, a novel activation calibration method for Post-Training Quantization (PTQ) that significantly reduces accuracy loss in Convolutional Neural Networks (CNN). Motivated by the need for high-fidelity quantization without costly retraining, MinMAE directly minimizes the Mean Absolute Error (MAE) between original and dequantized activations, making it robust to outliers that degrade standard methods. ...

Added: May 3, 2026

Machine Learning Methods for Fast Evaluation of Static IR Drop Effect

Solovyev Roman A., Telpukhov Dmitry, Shafeev I. et al., Technologies 2026 Vol. 14 No. 3 Article 169

With the continuous scaling of semiconductor design technologies, evaluating static IR drop has become a critical bottleneck in the physical synthesis flow. This paper presents a machine learning-based framework that transforms the power delivery network (PDN) analysis problem into an image-to-image translation task using a U-Net architecture with MaxViT and EfficientNet encoders. By implementing a ...

Added: May 3, 2026

On the minimum number of maximal distance-k independent sets in trees

Taletskii D., / Series arXiv "math". 2026.

A vertex subset of a graph is called a \textit{distance-$k$ independent set} if the distance between any two of its distinct vertices is at least $k + 1$. For all $n,k \geq 1$, we determine the minimum possible number of inclusion-wise maximal distance-$k$ independent sets among all $n$-vertex trees. It equals~$n$ if $n \leq k ...

Added: May 1, 2026

Proceedings of the 2026 8th International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE)

Dayoub A., Suleiman E., IEEE, 2026.

2026 8th International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE) 1-3 April 2026 ...

Added: April 30, 2026

Интеллектуальный анализ данных в нефтегазовой отрасли

М.: ООО «Геомодель Развитие», 2024.

Интелшектуальный анализ данных в нефтегазовой отрасли, Калининград, Россия, 2024, ООО «Геомодель Развитие» ...

Added: April 29, 2026

Bioinspired Method of Agent Redistribution between Groups

Karpova Irina Petrovna, Pattern Recognition and Image Analysis 2025 Vol. 35 No. 4 P. 1138–1144

A solution to the problem of redistributing agents between groups based on simulating a form of social parasitism in ants known as slave-making is considered. To provide a comprehensive solution, the problem is integrated with a method of orientation based on visual landmarks and a compass, including route memorization and return. The models and mechanisms ...

Added: April 29, 2026

Natural hazard database from Internet publications: text mining with a large language model

Derkacheva A., Sakirkina M., Kraev G. et al., /. 2026.

Comprehensive data on natural hazards and their consequences are crucial for effective for risk assessment, adaptation planning, and emergency response. However, many countries face challenges with fragmented, inconsistent, and inaccessible data, particularly regarding local-scale events. To address this data gap in Russia, we developed an end-to-end processing pipeline that scrapes news from various online sources, ...

Added: April 28, 2026

Analytical review of methods for identifying emotions in text data

Dvoynikova A., Verkholyak O., Karpov A., CEUR Workshop Proceedings 2020 Vol. 2552 P. 8–21

The sentiment analysis of text is one of the important tasks in the field of natural language processing. It is used in different areas. Despite the variety of existing methods, the systems of sentiment analysis of Russian-language texts give low accuracy compared to English-language ones. The article discusses basic methods for identifying emotions in text ...

Added: April 24, 2026

Decision-Making in Computational Intelligence-Based Systems: New Approaches, Methods, and Applications

Cham: Springer, 2026.

This book delivers actionable insights through 21 peer-reviewed chapters featuring new methods, models, and applications based on computational intelligence. Discover cutting-edge tools to support smart, efficient decision-making in complex, real-world scenarios. Organized into three parts—prescriptive analytics, soft computing models, and practical case studies—it spans domains such as healthcare, energy, mobility, finance, and public services. Readers ...

Added: March 17, 2026

Tackling the challenge of ML-assisted antibacterial activity prediction: One step closer to controlled quaternary ammonium compounds design via neural networks model

Ilin E., Frolov N., Seferyan M. et al., Bioorganic Chemistry 2025 Vol. 167 Article 109175

The ongoing rise of resistant bacterial pathogens poses a significant threat to current antibacterials' effectiveness putting millions of people's lives at risk. However, modern machine learning (ML) tools promise to tip the scales in the never-ending development of antimicrobial agents' pipelines. Herein we present a novel approach for quaternary ammonium compounds (QACs) antibacterial activity prediction ...

Added: March 16, 2026

POPULATION AND WORKPLACES ESTIMATION USING MACHINE LEARNING AND OPEN DATA SOURCES

Kiselev G., Prokhorov A., Journal of Mathematical Sciences. Vol. 295, No. 2, December, 2025. Mathematical Modeling and AI for Traffic Flows on Networks and Related Topics 2025 No. 295 P. 185–196

We study the problem of estimating the population and workplaces in a given area using open data sources and machine learning algorithms for automation and improvement of quality and accuracy of the transport demand calculation in transport modeling. Bibliography: 6 titles. Illustrations: 7 figures. ...

Added: March 12, 2026