Research areas

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.

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.

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

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.

Probabilistic machine learning describes methods which enable reasoning and inference over unknown quantities. Commonly used in generative modelling, regression and uncertainty quantification.

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.

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.

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.

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.

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.

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.

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.

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

Image segmentation is a long-standing pixel-level problem in computer vision, which can also serve as a testbed for other dense prediction tasks.

Constructing high-quality data representations are a necessary component in common machine learning pipelines.

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.

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.

Bayesian Methods are a subset of Probabilistic ML which provides a normative theory of ML and the ability to reason over subjective unknowns and handle epistemological uncertainties.