• A
  • A
  • A
  • АБВ
  • АБВ
  • АБВ
  • A
  • A
  • A
  • A
  • A
Обычная версия сайта
  • RU
  • EN
  • HSE University
  • Publications
  • Book chapter
  • Star-Shaped Denoising Diffusion Probabilistic Models
  • RU
  • EN
Расширенный поиск
Высшая школа экономики
Национальный исследовательский университет
Priority areas
  • business informatics
  • economics
  • engineering science
  • humanitarian
  • IT and mathematics
  • law
  • management
  • mathematics
  • sociology
  • state and public administration
by year
  • 2028
  • 2027
  • 2026
  • 2025
  • 2024
  • 2023
  • 2022
  • 2021
  • 2020
  • 2019
  • 2018
  • 2017
  • 2016
  • 2015
  • 2014
  • 2013
  • 2012
  • 2011
  • 2010
  • 2009
  • 2008
  • 2007
  • 2006
  • 2005
  • 2004
  • 2003
  • 2002
  • 2001
  • 2000
  • 1999
  • 1998
  • 1997
  • 1996
  • 1995
  • 1994
  • 1993
  • 1992
  • 1991
  • 1990
  • 1989
  • 1988
  • 1987
  • 1986
  • 1985
  • 1984
  • 1983
  • 1982
  • 1981
  • 1980
  • 1979
  • 1978
  • 1977
  • 1976
  • 1975
  • 1974
  • 1973
  • 1972
  • 1971
  • 1970
  • 1969
  • 1968
  • 1967
  • 1966
  • 1965
  • 1964
  • 1963
  • 1958
  • More
Subject
News
October 8, 2026
HSE Experts Take Part in 23rd Annual Meeting of Valdai Discussion Club
The 23rd Annual Meeting of the Valdai Discussion Club was held from September 28 to October 1, 2026 under the theme ‘Responsibility for the Future: Limits of the Possible, or Limitless Possibilities?’ The forum brought together 120 experts from 40 countries, including representatives of China, the United States, India, Brazil, the United Kingdom, Germany, Egypt, Iran, and Japan.
October 7, 2026
‘Our Team Consists of True Leaders in Their Respective Academic Disciplines
The HSE International Centre of Decision Choice and Analysis studies a wide range of methods for analysing decision-making and possible scenarios for the development of natural, socio-economic, and political phenomena using various mathematical models. The application of advanced mathematical methods to forecasting helps to prevent negative outcomes and avoid erroneous decisions. The HSE News Service spoke to the centre’s director, Prof. Fuad Aleskerov, about its work.
October 6, 2026
International N5 Symposium ‘Neural Networks and Nonlinearity in Nizhny Novgorod Brings Together Scientists from Russia and Serbia
The International N5 Symposium ‘Neural Networks and Nonlinearity in Nizhny Novgorod’ was held at the Nizhny Novgorod House of Scientists from September 23 to 26. The event was organised by HSE University–Nizhny Novgorod and the Nizhny Novgorod House of Scientists, with the participation of Sberbank and the Institute of Physics Belgrade. The symposium was held for the second time: the first conference took place in 2025 and attracted considerable interest from the academic community.

 

Have you spotted a typo?
Highlight it, click Ctrl+Enter and send us a message. Thank you for your help!

Publications
  • Books
  • Articles
  • Chapters of books
  • Working papers
  • Report a publication
  • Research at HSE

?

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 интеллектмашинное обучениедиффузионные моделиmachine learningdeep learning generative modelingгенеративное моделированиеглубокое обучениеartificial intellegencediffusion models

In book

Advances in Neural Information Processing Systems 36 (NeurIPS 2023)
Curran Associates, Inc., 2023.
Similar publications
Систематический обзор факторов принятия искусственного интеллекта студентами высших учебных заведений: образовательный контекст
Мухамедкаримова Д. Ф., Умуркулова М. М., Galyapina V. N. et al., Вестник Карагандинского университета. Серия Педагогика 2026 Т. 31 № 3 С. 69–77
Currently, artificial intelligence occupies a solid place among traditional pedagogical technologies and approaches, which is the subject of widespread discussion among domestic and foreign scientists and researchers. This is because the introduction of AI into higher education, despite its high potential, faces a wide range of economic, social, and ethical obstacles. These include resistance to ...
Added: October 6, 2026
Отношение россиян к искусственному интеллекту
Roshchina Y., Strebkov D., Roshchin S. et al., В кн.: Вестник Российского мониторинга экономического положения и здоровья населения НИУ ВШЭ (RLMS‑HSE). Вып. 16Вып. 16.: М.: Национальный исследовательский университет "Высшая школа экономики", 2026. С. 102–123.
The article examines the level of awareness, patterns of usage, and prevailing attitudes toward Artificial Intelligence (AI) in Russia. The study relies on data from an AI‑related questionnaire incorporated into the 2024 round of the Russia Longitudinal Monitoring survey – Higher School of Economics (RLMSHSE) and Google/Ipsos Multi‑Country AI Survey carried out in 2023. The ...
Added: October 5, 2026
Enhancing Boundary Stability in Decision Trees and Random Forests: A Weighted Sample Duplication Approach
Konstantinov A., Elizarova Anastasiya P., Utkin L., Computing, Telecommunications and Control 2026 Vol. 19 No. 1 P. 16–25
Decision trees and their ensemble extensions, such as random forests, are widely used as classification models due to their simplicity and interpretability. However, in many real-world tasks where class labels overlap in the feature space, standard decision trees rely on hard splits that create fragile decision boundaries. In these regions, small perturbations in the input ...
Added: October 2, 2026
Роль и место преподавателя в экосистеме университетского предпринимательства: российский опыт
Sorokin P., Morozova E., Goshin M. E. et al., Высшее образование в России 2026 Т. 35 № 3 С. 63–89
The purpose of this study is to empirically identify the potential of contemporary educators involved in university entrepreneurship support initiatives as potential drivers of ecosystem development. This is achieved through an analysis of their key individual characteristics, professional experience, pedagogical practices, and the institutional context of the university environment. To this end, based on a ...
Added: October 2, 2026
Urbi et Orbi («Городу и миру»): «Ценности открытого мира и «железного занавеса». Сборник
М.: ООО «Городу и миру», 2026.
Как мочили «Яблоко» и чем хороша Партия наивных дураков, кто вывел в люди советскую науку и что такое «русский ИИ». ...
Added: October 2, 2026
ПРИЕМКА КОРПОРАТИВНОГО ИИ-ПОИСКА ОБОСНОВАНИЕ РЕШЕНИЯ
Белов Б. П., Kocharian R., Самойлов И. А. et al., Стандарты и качество 2026 № 10 С. 105–109
Acceptance of enterprise AI search requires checking answer correctness and access controls, defining acceptable errors, and assessing whether testing is sufficient. A record for individual acceptance criteria was developed. Its eight fields link requirements and risks to system configuration, testing, and the acceptance decision. The fields are mapped to provisions in four Russian standards. The ...
Added: October 1, 2026
Формирование Китаем технологического суверенитета в области «физического ИИ»: кейс промышленной робототехники
Klochko O., Кузнецова М. П., Пространственная экономика 2026 Т. 22 № 3 С. 73–103
The article assesses China’s technological sovereignty in high-tech industries that form the ecosystem of physical artificial intelligence and its readiness to develop intelligent robotics. The aim of the study is to identify changes in China’s position in the global value chains of these industries through a comprehensive analysis of foreign value added used in production, ...
Added: October 1, 2026
Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence (IJCAI 2026)
International Joint Conferences on Artificial Intelligence, 2026.
Added: October 1, 2026
Изменение структуры мировой экономики: от очевидных сдвигов к стратегической неопределенности
Belousov D., Экономическое возрождение России 2026 № 2 С. 85–97
Выявление ключевых тенденций и структурных сдвигов в развитии мировой экономики, обусловленных переходом от биполярной модели к «мозаичному» миру взаимодействующих центров силы, а также определение возможных позиций и роли России в формирующейся новой архитектуре международных экономических отношений в современных условиях приобретает важное не только теоретическое, но и прикладное значение. В результате исследования зафиксирован парадоксальный феномен: в ...
Added: September 29, 2026
Дополнительная коррекция ошибок в каскадном коде с помощью полносвязных нейронных сетей
Portnoy S., Efremov A., Кузьмин В. В., В кн.: Распределенные компьютерные и телекоммуникационные сети: управление, вычисление, связь (DCCN-2026): материалы XXIX Международной научной конференции. Россия, Москва, 21–27 сентября 2026 г.: М.: РУДН, 2026..
В работе рассматривается возможность улучшения помехоустойчивости каскадного кода, состоящего из внутреннего кода Хэмминга (4,3) и внешнего кода Рида — Соломона (7,5) над полем GF(8), за счёт дополнительной кор рекции ошибок на основе машинного обучения. Внешний код декодируется списочным алгоритмом с перебором стираний; рассматриваются списки дли ной 5 и 10 комбинаций. Для компенсации потерь помехоустойчивости при ...
Added: September 26, 2026
Экспертная оценка ответов больших генеративных моделей на запросы врачей в клинической практике
Тыров И. А., Васильев Ю. А., Владзимирский А. В. et al., Труды Института системного анализа Российской академии наук 2026 Т. 76 № 3 С. 79–89
Large language models (LLMs) in healthcare currently attract significant interest. This study compared GigaChat and YandexGPT by evaluating 1,200 LLM-generated responses to physician queries from outpatient and inpatient settings across 7 topics. Thirteen expert physicians assessed the responses using a 5-point scale across five criteria: relevance, correctness, safety, completeness, and language literacy. We performed paired ...
Added: September 22, 2026
Функциональная агентность искусственного интеллекта: типология и градуальный подход
Karpenko I., Человек 2026 Т. 37 № 5 С. 42–58
This article examines the question of agency in artificial intelligence systems. A distinction is proposed between three types of agency: ontological, functional, and ascribed. The central thesis is that functional agency is a genuine rather than metaphorical type, which is grounded through the teleological theory of function and through a critique of the argument from ...
Added: September 16, 2026
Использование методов машинного обучения для повышения эффективности систем противодействия многоэтапных кибератак
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
Может ли ИИ производить значение? Семантический капитал, «стохастический попугай» и пределы антропоцентризма
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
Применение технологий компьютерного зрения в системах обработки визуальной информации
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
  • About
  • About
  • Key Figures & Facts
  • Sustainability at HSE University
  • Faculties & Departments
  • International Partnerships
  • Faculty & Staff
  • HSE Buildings
  • HSE University for Persons with Disabilities
  • Public Enquiries
  • Studies
  • Admissions
  • Programme Catalogue
  • Undergraduate
  • Graduate
  • Exchange Programmes
  • Summer University
  • Summer Schools
  • Semester in Moscow
  • Business Internship
  • Research
  • International Laboratories
  • Research Centres
  • Research Projects
  • Monitoring Studies
  • Conferences & Seminars
  • Academic Jobs
  • Yasin (April) International Academic Conference on Economic and Social Development
  • Media & Resources
  • Publications by staff
  • HSE Journals
  • Publishing House
  • iq.hse.ru: commentary by HSE experts
  • Library
  • Economic & Social Data Archive
  • Video
  • HSE Repository of Socio-Economic Information
  • HSE1993–2026
  • Contacts
  • Copyright
  • Privacy Policy
  • Site Map
Edit