Research areas

Tabular data involves two-dimensional tables with objects (rows) and features (columns), which are used in numerous applied tasks such as classification, regression, ranking and many others.

Today, training most powerful models often takes significant resources. Our research aims to make large-scale training more efficient and accessible to the entire machine learning community.

Generative models in computer vision are powerful tool for various applications.

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.

Algorithmic reasoning focuses on building models that can execute classic algorithms. It allows one to combine the advantages of neural networks with theoretical guarantees of algorithms.

Yandex Research team regularly contributes to the computer vision research community, mostly in the field of image retrieval and generative modelling.

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

We study various aspects related to theoretical understanding of ML models and algorithms.

Nearest neighbor search is a long-standing problem arising in a large number of machine learning applications, such as recommender services, information retrieval, and others.

Most machine learning algorithms build an optimization model and learn its parameters from the given data. Thus, developing effective and efficient optimization methods is of the essence.

Learning to rank is a central problem in information retrieval. The objective is to rank a given set of items to optimize the overall utility of the list.

Gradient boosting iteratively combines weak learners (usually decision trees) to create a stronger model. It achieves state-of-the-art results on tabular data with heterogeneous features.

Uncertainty estimation enables detecting when ML models make mistakes. This is of critical importance in high risk machine learning applications, such as autonomous vehicle and medical ML.

Distributional shift is the mismatch between training and deployment data that is ubiquitous in the real-world. Studying this phenomenon can enable safer and more reliable ML systems.

Language barriers hinder global communication and access to worldwide knowledge. By improving machine translation systems, we hope to facilitate the exchange of culture and information.

Training and running large neural networks efficiently across many devices, whether in a GPU cluster or a swarm of poorly connected consumer devices.

Speech is an important data modality and relatives to applications such as speech recognition and speech synthesis, which are core technologies in products such as vocal assistants.

Deep learning models are outgrowing the hardware that runs them. We try to make large models fit on smaller devices through quantization, pruning, factorization, and other means.

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.