• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Centre of Deep Learning and Bayesian Methods

Social networks of the Center
Publications
Working paper
Compressed and Smooth Latent Space for Text Diffusion Modeling.

Meshchaninov V., Chimbulatov E., Shabalin A. et al.

Computation and Language. cs.CL, arXiv:2506.21170. Cornell University, 2025

Book chapter
Revisiting Non-Acyclic GFlowNets in Discrete Environments

Morozov N., Maximov I. V., Tiapkin D. et al.

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

Book chapter
TEncDM: Understanding the Properties of the Diffusion Model in the Space of Language Model Encodings
In press

Shabalin A., Meshchaninov V., Chimbulatov E. et al.

In bk.: Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence. Vol. 39. Iss. 23. United States of America; Washington: AAAI Press, 2025. Ch. 110. P. 25110-25118.

Book chapter
Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization

Timofei Gritsaev, Morozov N., Samsonov S. et al.

In bk.: Proceedings of the 13th International Conference on Learning Representations (ICLR 2025). ICLR, 2025. P. 95626-95646.

Working paper
Mechanistic Permutability: Match Features Across Layers

Balagansky N., Ian Maksimov, Daniil Gavrilov.

arxiv.org. Computer Science. Cornell University, 2024

About the Center

The center conducts research at the intersection of two actively developing areas of data analysis: deep learning and Bayesian methods of machine learning methods. Deep learning is a section that involves building very complex models (neural networks) to solve problems such as classifying images or music, transferring an art style from picture to photograph, predicting the next words in a text. Within the framework of the Bayesian approach, probabilistic models based on the apparatus of probability theory and mathematical statistics are considered for solving such problems.

The center was created on the basis of the Dmitry Vetrov's Bayesian Methods Research Group.


Illustration for news: HSE Lecturers Awarded Yandex ML Prize 2025

HSE Lecturers Awarded Yandex ML Prize 2025

The Yandex ML Prize is awarded to lecturers and heads of educational programmes who contribute to the development of artificial intelligence in Russia. This year, 10 laureates were selected from 300 applicants, including three members of the HSE Faculty of Computer Science (FCS). A special Hall of Fame award was also presented for contributions to the establishment of machine learning as an academic field. One of the recipients was Dmitry Vetrov, Research Professor at the HSE FCS.

Illustration for news: Technological Breakthrough: Research by AI and Digital Science Institute Recognised at AI Journey 2025

Technological Breakthrough: Research by AI and Digital Science Institute Recognised at AI Journey 2025

Researchers from the AI and Digital Science Institute (part of the HSE Faculty of Computer Science) presented cutting-edge AI studies, noted for their scientific novelty and practical relevance, at the AI Journey 2025 International Conference. A research project by Maxim Rakhuba, Head of the Laboratory for Matrix and Tensor Methods in Machine Learning, received the AI Leaders 2025 award. Aibek Alanov, Head of the Centre of Deep Learning and Bayesian Methods, was among the finalists.