Follow our latest advances in machine learning.

Generative models

Graph machine learning

Computer vision

Distributional shift

Natural language processing 

Nearest neighbor search

Uncertainty estimation 

Large-scale machine learning

Machine learning theory

Neural algorithmic reasoning

Tabular data

Distributed ML

Gradient boosting

Speculative and parallel decoding

Blog

Yandex Research Blog

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

Papers accepted to ICLR 2026

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 GraphPFN, a graph foundation model that extends the prior-data fitted network (PFN) framework to graphs, achieving state-of-the-art in-context and finetuned results on real-world graphs.

GraphPFN: a graph foundation model pretrained on diverse synthetic graphs

In 2025, Yandex Research teams continued to work in the following areas: efficient large language models (LLMs), optimization, tabular deep learning, graph machine learning, as well as applied and scientific research in the field of generative computer vision and projects related to YandexART.

Yandex Research in 2025

Five papers by the Yandex Research team and our collaborators have been accepted for publication at the Conference on Neural Information Processing Systems (NeurIPS 2025).

Papers accepted to NeurIPS 2025

Six papers by the Yandex Research team (shown in bold below) and our collaborators have been accepted for publication at the International Conference on Machine Learning (ICML 2024).

Blog

Posts

Papers accepted to ICLR 2026

GraphPFN: a graph foundation model pretrained on diverse synthetic graphs

Yandex Research in 2025

Papers accepted to NeurIPS 2025

Papers accepted to ICML 2025

Filter by: