• A
  • A
  • A
  • АБВ
  • АБВ
  • АБВ
  • A
  • A
  • A
  • A
  • A
Обычная версия сайта
  • RU
  • EN
  • HSE University
  • Publications
  • Book chapter
  • Cache Me If You Must: Adaptive Key-Value Quantization for Large Language 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
  • 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
August 18, 2026
HSE Scholar Presents Research on Postcards in Brazil and South Korea
Timur Khusyainov, Deputy Dean of theFaculty of Humanities atHSE University–Nizhny Novgorod, took part in two international conferences—the XVI World Congress of Rural Sociology in Porto Alegre, Brazil, and the 36th Annual Conference of the Alliance of Digital Humanities Organisations (DH2026) in Daejeon, South Korea. On his way to the conferences, the researcher also visited several other places, where he presented the experience of the Pochtovoe educational project.
August 18, 2026
Physicists Discover What Happens Inside a Stable Vortex
Large vortices with characteristic spiral arms are often observed in the atmosphere and the ocean. Physicists from HSE University have explained how these structures form and why they retain their shape. The researchers found that velocities at points located along the same vortex arc remain correlated even over long distances. At the same time, this correlation weakens rapidly with increasing distance from the vortex centre. These differences help explain the formation of spiral arms and may improve models of atmospheric and oceanic currents. The findings have been published in Physical Review Fluids.
August 17, 2026
‘I Dream of Simple Things
Anastasia Gergenreter specialises in applied statistics and econometrics. In this interview for the Young Scientists of HSE University project, she talked about why she studies addictive substance use, two very different Fishers, and the cherry blossom season at the Main Botanical Garden in Moscow.

 

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

?

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

.
Alina Shutova, Vladimir Malinovskii, Vage Egiazarian, Denis Kuznedelev, Ivan Ermakov
Language: English
Text on another site
Keywords: large language models

In book

Volume 267: International Conference on Machine Learning, 13-19 July 2025, Vancouver Convention Center, Vancouver, Canada
Vol. 267. , [б.и.], 2025.
Similar publications
Персонализированная обратная связь на основе искусственного интеллекта: модель для магистратуры гуманитарного профиля
Подболотова М. И., Адамский А. И., Kolachev N. et al., Высшее образование в России 2026 Т. 35 № 4 С. 21–35
The purpose of the article is to present and justify a pedagogical model of personal ized feedback based on large language models (LLM) for the educational process in a human ities-oriented master’s program. The relevance of the study is determined by the objectives of digital transformation of higher education in the Russian Federation, outlined in Presidential Decree No. 474 ...
Added: May 4, 2026
Artificial Intelligence in Textual Biographical Research: A Systematic Review of Methods, Effectiveness, and Epistemological Limits
Mikhaylova O., Life Writing 2026 Vol. 23 No. 3 P. 550–567
Biographical research relies on rich life narratives but now faces scalability pressures as digital archives and clinical interview corpora expand. This systematic review synthesizes 56 empirical studies (2014–2025) that applied artificial intelligence or computational methods to textual biographical data, including oral histories, life history interviews, autobiographical narratives, clinical life stories, and memoirs. Studies were coded ...
Added: March 30, 2026
Применение больших языковых моделей для анализа ценностно-патриотического дискурса русскоязычных пользователей
Balakina Y. V., Grigoreva M., Соколова Е. Н., Вестник Российского фонда фундаментальных исследований. Гуманитарные и общественные науки 2025 Т. 123 № 4 С. 56–69
The article examines the potential of large language models (LLMs) for automated analysis of value-laden and patriotic discourse in Russian-language social media. Using a corpus of posts from VK, Odnoklassniki and Telegram (2023–2025), it investigates the extent to which automatic coding results align with expert annotation based on a specially developed categorical scheme. The codebook ...
Added: November 26, 2025
Новые интерфейсы и новые медиаторы
Maksimenkova O. V., Сегал А. П., Вопросы философии 2025 № 10 С. 67–76
The study is devoted to the humans and artificial intelligence (AI) interaction. The authors view this interaction as mediated by interfaces that both simplify it and hide the real mechanisms of encoding and decoding messages (according to Shannon). In such a situation, the characteristics of the actor of communication are blurred, and it is not ...
Added: October 2, 2025
Artificial Neural Networks and Machine Learning. ICANN 2025 International Workshops and Special Sessions: 34th International Conference on Artificial Neural Networks, Kaunas, Lithuania, September 9–12, 2025, Proceedings, Part V
Cham: Springer, 2025.
This book constitutes the refereed proceedings of 34th International Workshops which were held in conjunction with the 34th International Conference on Artificial Neural Networks and Machine Learning, ICANN 2025, held in Kaunas, Lithuania, September 9–12, 2025.   The 20 full papers and 8 abstracts included in this workshop volume were carefully reviewed and selected from 42 submissions. ...
Added: September 29, 2025
Rewriting the Rules: LLMs Vs. Traditional ML in University Admissions
Chepikov I., Karpov I., , in: 26th International Conference, AIED 2025, Palermo, Italy, July 22–26, 2025, Proceedings, Part I. Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners, Doctoral Consortium, Blue Sky, and WideAIED.: Springer, 2025. P. 352 – 358.
Modern LLM models such as BERT, ChatGPT, DeepSeek have shown great potential in solving various tasks, including text classification, text generation, analysis and summary of documents. In this paper, we show that these models close to classical ML approaches based on decision trees not only in text processing, but also in processing classical tabular data ...
Added: September 4, 2025
Verification of linguistic hypotheses applying large language models
Фирсанова В. И., Вестник Череповецкого государственного университета 2025 Vol. 124 No. 1 P. 80–90
The paper proposes a novel approach to the verification of linguistic hypotheses applying large language models. The method uses a formal description of a linguistic theory to be proven to build a vector representation for a collection of language data. The representation is compared with embeddings constructed with help of neural network models. The research ...
Added: July 10, 2025
Распознавание рукописного текста и интеллектуальный анализ: возможности нейронных технологий (на примере работы с «Дневником» Ф.П. Литке)
Boltunova E., Laptev A., Имагология и компаративистика 2025 № 23 С. 358–379
Added: June 16, 2025
Оценивание студенческих работ в рамках обучения академическому письму на английском языке в контексте развития инструментов искусственного интеллекта
Bakulev A., В кн.: Профессионализм учителя иностранных языков и его реализация. Сборник статей по материалам научно-методического симпозиума с международным участием «Лемпертовские чтения – XXVII» 15-17 мая 2025 года.: Пятигорск: Издательство Пятигорского государственного университета, 2025. С. 270–279.
The paper focuses on assessing students’ written papers in the discipline “Academic Writing in English in the context of AI tools’ capabilities. AI tools, specifically large language models (LLMs) appear to be able to tackle and solve a wide range of educational and research tasks. Foreign language teaching is no exception: AI tools are utilized ...
Added: June 5, 2025
Generative AI-based Approach to Concept Drift Generation in Streaming Text Data
Belov B., Peter Panfilov, WSEAS Transactions on Information Science and Applications 2025 Vol. 22 P. 11–20
Real-time analysis of text streams is crucial for industrial and business processes and scenarios. It is expected to be  one of the important future research topics in the text processing and understanding domain. Analysis of text data is based on the use of pre-trained machine learning/data mining (ML/DM) models that may demonstrate performance degradation over ...
Added: April 5, 2025
Роль больших языковых моделей в интегрированных средах разработки нового поколения
Ишанхонов А. Ю., Pshichenko D., Можаровский Е. А. et al., Программные системы и вычислительные методы 2024 № 4 С. 140–150
The role of Large Language Models (LLM) in new generation integrated development environments (IDEs). Tools such as GitHub Copilot, IntelliCode and Alice Code Assistant are explored in the context of their use in programming. The authors examine how LLMs enable the automation of key development tasks, including code autocompletion, error detection, refactoring, and code generation, ...
Added: March 10, 2025
Ensuring trustworthy code: leveraging a static analyzer to identify and mitigate defects in generated code
D. Shaikhelislamov, Drobyshevskiy M., A. Belevantsev, Journal of Mathematical Sciences 2024 Vol. 540 P. 233–251
The rise of large language models (LLMs) has greatly advanced code generation capabilities. A recent StackOverflow survey found that 70% of developers are using or planning to use AI coding tools this year. However, most current methods focus on supervised fine-tuning objectives derived from text generation, often overlooking the distinct sequence-level properties of code, such as compilability, and ...
Added: February 3, 2025
Управление знаниями организации и большие языковые модели
Zelenkov Y., Российский журнал менеджмента 2024 Т. 22 № 3 С. 573–601
Purpose: to summarize, classify and analyze current scientific publications on the use of large language models (LLM) in knowledge management in organization. Methodology: systematic literature review was conducted. It was based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) framework. 75 publications were selected for analysis, including academic articles and reports of consulting companies published ...
Added: January 4, 2025
ChatGPT, текст, информация: критический анализ
Komashko M. N., Труды по интеллектуальной собственности 2024 Т. 50 № 3 С. 118–128
The paper deals with theory and practice issues related to such type of artificial intelligence as large language models, in particular, ChatGPT. The main attention is paid to spheres of human activity, in which the exchange of information stated in the form of text is of the greatest importance: science, education and journalism (media sphere). The ...
Added: December 29, 2024
DAREL: Data Reduction with Losses for Training Acceleration of Real and Hypercomplex Neural Networks
Demidovskij A., Трутнев А. И., Тугарев А. М. et al., / Series ZmuLcqwzkl "NeurIPS 2023 Workshop". 2023.
Neural network training requires a lot of resources, and there are situations where training time and memory usage are limited. It makes specialized algorithms for training neural networks within the constraints of resource limitations an important and significant challenge. Data Reduction with Losses is a novel training data reduction method that operates with training samples ...
Added: January 17, 2024
  • 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