Follow our latest advances in machine learning.

Graph machine learning

Generative models

Computer vision

Natural language processing 

Distributional shift

Nearest neighbor search

Uncertainty estimation 

Large-scale machine learning

Machine learning theory

Neural algorithmic reasoning

Speculative and parallel decoding

Tabular data

Distributed ML

Gradient boosting

Blog

Yandex Research Blog

Language is one of the key forms of communication. We study methods of language representation and understanding to simplify human-computer interactions.

Modern LLMs are autoregressive models that generate one token at a time, which is inefficient on parallel hardware. These works accelerate generation by processing multiple tokens per forward pass.

Our thoughts and recent work on how sharing and scheduling KV-cache state lets pretrained LLMs observe, reason, and act concurrently without additional training

The KV cache as an agent runtime

Graphs are a natural way to represent data from various domains such as social networks, molecules, text, code, etc. We develop and analyze algorithms for graph-structured data.

We introduce a set of IO-Aware kernels for Graph Neural Networks, bridging the gap between large-scale Graph Machine Learning and hardware-efficient deep learning. The paper was accepted at ICML 2026 as a Spotlight Paper.

On efficient scaling of GNNs via IO-aware layer implementations

Eight papers by the Yandex Research team and our collaborators have been accepted for publication at the International Conference on Machine Learning (ICML 2026).

Papers accepted to ICML 2026

Our paper has been accepted for publication at the Conference on Computer Vision and Pattern Recognition (CVPR 2026).

Paper accepted to CVPR 2026

Six papers by the Yandex Research team and our collaborators have been accepted for publication at the International Conference on Learning Representations (ICLR 2026).

Blog

Posts

The KV cache as an agent runtime

On efficient scaling of GNNs via IO-aware layer implementations

Papers accepted to ICML 2026

Paper accepted to CVPR 2026

Papers accepted to ICLR 2026

Filter by: