Star-Shaped Denoising Diffusion Probabilistic Models

Andrey Okhotin; Dmitry Molchanov; Arkhipkin V.; Grigory Bartosh; Viktor Ohanesian; Aibek Alanov; Dmitry Vetrov

Publications

?

Star-Shaped Denoising Diffusion Probabilistic Models

P. 10038–10067.

Andrey Okhotin, Dmitry Molchanov, Arkhipkin V., Grigory Bartosh, Viktor Ohanesian, Aibek Alanov, Dmitry Vetrov

Language: English

Full text

Text on another site

Keywords: искусственный интеллект машинное обучение диффузионные модели machine learning deep learning generative modeling генеративное моделирование глубокое обучение artificial intellegence diffusion models

In book

Advances in Neural Information Processing Systems 36 (NeurIPS 2023)

Curran Associates, Inc., 2023.

Банки и экосистемы

Бровкина Н. Е., Терновская Е. П., Мешкова Е. И. et al., В кн.: Банк в современной экономикеКн. Банк в современной экономике.: М.: КноРус, 2026. С. 127–147.

Banks are the central link in the national financial market and the economy as a whole. The share of bank assets in the asset structure of the Russian financial market, despite a slight decline, remains dominant relative to other participants, reaching 80%. Russian banks are multifaceted. On the one hand, they provide working capital financing, long-term ...

Added: September 3, 2026

Цифровой двойник: правовая природа, уровни и опыт Бразилии

Shchennikova I., Закон 2026 № 8 С. 84–93

Digital twin technology is widely used in various sectors of the economy, modeling subjects and objects based on data about them and the environment surrounding them. In the broadest sense, the goal of a digital twin is to solve a problem including the problem of studying of the modeled subject or object and ensuring its ...

Added: August 28, 2026

Асимметрия информации на рынке адвокатских услуг: создание рейтинга методами машинного обучения

Kazun A., Девятников В. Ю., Белов М. Д., Вопросы теоретической экономики 2026 Т. 3 № 32 С. 115–135

Как понять, хорош адвокат или нет? В данной статье мы описываем методологию, позволяющую измерять качество юридической помощи через разницу между тем, что предсказывает модель машинного обучения по объективным характеристикам дела, и тем, чем дело закончилось в реальности. Мы исходим из предпосылки, что если у адвоката дела стабильно заканчиваются лучше ожидаемого, то он делает свою работу хорошо. ...

Added: August 28, 2026

Шизофрения и её влияние на лексический уровень языка

Tasenko O., Untila K., Shishkovskaya T. et al., В кн.: Десятая международная конференция по когнитивной науке: Тезисы докладов. Пятигорск, 26–30 июня 2024 г.: Пятигорск: ОПиИД УНР ФГБОУ ВО «ПГУ», 2024. С. 328–329.

Шизофрения – это хроническое психическое расстройство, которое выражается как комбинация психотических симптомов, таких как галлюцинации, бред и дезорганизация когнитивных функций. Для шизофрении характерны трудности с поиском слов, приближение слов, то есть использование сходных по значению с нужным или же описывающих предполагаемое значение, а также использование негативной лексики чаще, чем в группе нормы, в том числе при описании ...

Added: August 24, 2026

VOLATILITY FORECASTING FROM ECONOMETRICS TO ARTIFICIAL INTELLIGENCE: A FOUR-STAGE REVIEW OF THE EVIDENCE PIPELINE FROM FORECAST ACCURACY TO PORTFOLIO PERFORMANCE

Lysenok N., International Journal of Computer Information Systems and Industrial Management Applications 2026 Vol. 18 No. 18s P. 1406–1430

A volatility forecast becomes useful only after it has passed through four stages: a model produces it, a trading rule consumes it, a portfolio aggregates the result, and an investor evaluates that result against a utility function. Each stage has its own mature evaluation apparatus, and each is studied in isolation. This review traces the ...

Added: August 23, 2026

Which Model Families Pay? Econometric, Gradient Boosting and Recurrent Neural Network Volatility Forecasts in Active Trading Strategies on the Russian Stock Market

Nikita I. Lysenok, International Journal of Computer Information Systems and Industrial Management Applications 2026 Vol. 18 No. 17s P. 533–549

This paper asks which families of volatility forecasting models create economic value in active trading, and through which integration channel that value is transmitted. Seven models drawn from four families — econometric (GJR-GARCH, HAR-J), gradient boosting (XGBoost, LightGBM), recurrent neural networks (LSTM, GRU) and a hybrid combining HAR-J with boosting — are compared on the ...

Added: August 18, 2026

Cambodia's Policy on the Artificial Intelligence: Determinants, Directions, Interim Outcomes

Kanaev E., Southeast Asia: Actual Problems of Development 2026 Vol. 1 No. 1(70) P. 153–163

The article aims to specify the degree of success Cambodia has been able to achieve in developing its Artificial Intelligence (AI) ecosystem seen through the prism of the state of the country’s non-digital assets as an outcome of its economic modernization, as well as of its digital projects and initiatives. Outlining the specifics of Cambodia’s ...

Added: July 30, 2026

ASEAN and the Resolution of the South China Sea Issue: Assessing Digital Limitations

Kanaev E., Southeast Asia: Actual Problems of Development 2026 Vol. 2 No. 2(71) P. 11–22

The author focuses on a strengthening digital component in the evolution of the South China Sea issue in the context of ASEAN’s evolving approach to the deepening contradictions and its policy in the digital field. On outlining ASEAN’s policy on the South China Sea issue, the author proceeds to exploring the digital agenda of ASEAN’s ...

Added: July 30, 2026

Ответственность за вред, причиненный с использованием технологии искусственного интеллекта: проблемы и перспективы европейской гармонизации

Иноземцев М. И., Stepanov S., Закон 2026 № 7 С. 193–203

In 2022, the European Commission introduced a draft directive on liability for harm caused through the use of artificial intelligence systems. The hallmark of the proposal lies in its decision to retain a fault-based liability regime, even when harm arises in connection with the deployment of AI technologies. The draft further includes several procedural mechanisms ...

Added: July 27, 2026

Проникновение искусственного интеллекта в жизненный цикл разработки программного обеспечения: эмпирический анализ рынка труда

Stoyanova O., Окусков И. С., Бизнес-информатика 2026 Т. 20 № 2 С. 81–93

The integration of artificial intelligence (AI) into information technologies is reshaping competency requirements for IT specialists. However, AI competency penetration into the early phases of the Software Development Life Cycle (SDLC) – requirements analysis and planning – remains underexplored. Existing studies either rely on static competency models lacking empirical validation or analyze the labor market ...

Added: July 5, 2026

Правовые аспекты обработки синтетических данных

Лескина Э. И., Вестник Воронежского государственного университета. Серия: Право 2026 Т. 65 № 2 С. 100–111

Society increasingly relies on generative artificial intelligence models, which are used in many areas and have become an integral part of the lives of various social groups. The exponential growth of data, however, cannot meet the ever-growing demand for training artificial intelligence models. A relatively new way to overcome the shortage of training data is ...

Added: July 2, 2026

Сравнение методов автоматической разметки речевых формул в русскоязычном интернет-дискурсе: пилотное исследование

Масленикова А. С., Попова Т. И., В кн.: Компьютерная лингвистика и интеллектуальные технологии: По материалам ежегодной международной конференции «Диалог». Выпуск 24Issue 24.: M.: Max press, 2026. С. 420–428.

This study focuses on developing and comparing methods for automatic annotation of speech formulas in a corpus of Russian internet comments. Speech formulas are a class of multiword expressions that convey emotional reactions in dialogue. The research material consisted of a corpus of 10,000 comments (157,261 tokens) collected from five Telegram channels. Dictionary-based formal search ...

Added: June 29, 2026

The Use of the Missing Sample Simulation Modeling to Create a Classification Model for Three or More Classes by the Example of the Carbohydrate Metabolism Disorder Degree Detection Problem

Новиков Р. С., Novopashin M., Pozin B., Programming and Computer Software 2026 Vol. 52 No. 1 P. 28 – 38

Added: June 26, 2026

Искусственный интеллект как институциональный вызов: диагностика дисфункций системы образования и науки и возможные регуляторные ответы

Капитонов И. А., Москвитин О. А., Современное профессиональное образование 2026 № 5 С. 55–57

В статье рассматривается проблема институциональной неготовности российской системы образования и науки к массовому распространению генеративного искусственного интеллекта. Авторы фиксируют парадоксальную асимметрию: студенты и аспиранты активно применяют ИИ для делегирования текстопроизводства, тогда как научно-педагогические работники в большинстве своём не используют его как исследовательский инструмент. Показано, что в основе этой асимметрии лежит не «злой умысел» участников, а ...

Added: June 23, 2026

К ранжированию значимости факторов дестабилизации в странах Азии и Африки методами машинного обучения

Korotayev A., Chernomorchenko I., Медведев И. А., Восток. Афро-азиатские общества: история и современность 2026 № 3 С. 117–130

This study employs machine learning methods to rank factors contributing to large-scale armed and unarmed destabilization across Asian and African countries. Analysis reveals that African nations demonstrate greater vulnerability to armed destabilization (up to full-scale civil wars), whereas Asian countries are more prone to less violent unarmed forms (mass antigovernment demonstrations, riots, general strikes and ...

Added: June 21, 2026

Социальное программирование как методологический инструмент сетевой самоорганизации: проблемы и тенденции (материалы «круглого стола»)

Pruzhinin B. I., Afanasov N., Буданов В. Г. et al., Вопросы философии 2026 № 5 С. 5–35

In December 2025, the Institute of Philosophy of the Russian Academy of Sciences hosted an international roundtable on the topic “Social Programming as a Methodological Tool of Network Self-Organization: Problems and Trends”. The roundtable was organized by the journal “Voprosy Filosofii” and representatives of the research project No. 25-28-00707, “Social Programming as a Problem of Network ...

Added: June 18, 2026

Automated detection of wolf howls using audio spectrogram transformers

Makarov N., Savchenko A., Zemtsova I. et al., Scientific Reports 2025 Vol. 15 Article 26641

The grey wolf (Canis lupus) is a pivotal species for ecological studies. As a key participant in ecosystem processes, it also serves as a model for investigating social structure formation and ecological adaptation. However, the species’ complex social behavior, spatial dynamics, and expansive habitats make monitoring and population assessments across large areas particularly challenging. In recent years, audio traps ...

Added: June 16, 2026

Artificial intelligence framework for multi-pathology risk assessment from retinal fundus images: deep learning approach to 15-disease screening

Vasilev R., Savchenko A., Blinov P. et al., Frontiers in Medicine 2026 Vol. 13 Article 1778404

Automated disease screening systems face challenges when applied to multi-class medical image analysis, particularly under severe class imbalance inherent in clinical datasets. Retinal fundus imaging enables non-invasive screening for multiple ocular and systemic diseases simultaneously, yet current automated systems typically assess risk for only a single pathology or a limited disease range. We developed a ...

Added: June 16, 2026