Eight papers have been accepted for publication at the Conference on Neural Information Processing Systems (NeurIPS 2023).

Papers accepted to NeurIPS 2023

This competition focuses on developing indexing data structures and search algorithms for practical settings of the Approximate Nearest Neighbor (ANN) or Vector search problem. More details are on the competition’s website. We encourage everyone to join by August 30th, 2023!


NeurIPS 2023 Competition Track: Big-ANN

A paper has been accepted for publication at the International Conference on Computer Vision (ICCV 2023). DeDrift: Robust Similarity Search under Content Drift by Dmitry Baranchuk, Matthijs Douse, Yash Upadhyay, Zeki Yalniz.

Paper accepted to ICCV 2023

At Yandex Research, we advance progress in science and develop technologies for a better tomorrow.

large_join.jpg

medium_join.jpg

small_join.jpg

thumbnail_join.jpg

join.jpg

Join our research team and get an opportunity to engage in world-class applied and theoretical research, gain experience working on high-impact projects and publish at top-tier academic conferences. You will contribute to high-tech services like computer vision technologies, dialogue systems, neural machine translation and self-driving cars. 

Work with us

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

Computer vision

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

Natural language processing 

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.

Large-scale machine learning

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

Machine learning theory

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.

Graph machine learning

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

Probabilistic machine learning

icon_post_8.svg

Neural algorithmic reasoning focuses on building models that can execute classic algorithms. It allows one to combine the advantages of neural networks, such as handling raw and noisy input data, with theoretical guarantees and strong generalization of algorithms. Assuming we have a neural network capable of solving a classic algorithmic task, we can incorporate it into a more complex pipeline and train end-to-end. For instance, if we have a neural solver aligned to the shortest path problem, it can be used as a building block for a routing system that accounts for complex and dynamically changing traffic conditions. In our work [ref1], we study algorithmic reasoners trained only from input-output pairs, in contrast to current state-of-the-art approaches that utilize the trajectory of a given algorithm. We propose several architectural modifications and demonstrate how standard contrastive learning techniques can regularize intermediate computations of the models without appealing to any predefined algorithm’s trajectory. 

Neural algorithmic reasoning without intermediate supervision

icon_post_14.svg

Diffusion models are currently the most powerful approach to generating images from a text description. One popular application is the adaptation of such models to new concepts: usually, it is quite difficult or even impossible to write a prompt that accurately describes the target object.

At the same time, existing methods are too slow for practical purposes. In “Is This Loss Informative? Faster Text-to-Image Customization by Tracking Objective Dynamics”, our paper accepted at NeurIPS 2023, we propose DVAR  — a lightweight early stopping criterion for gradient-based adaptation methods. Our experiments with Stable Diffusion show up to 8 times acceleration with minor losses in the quality of identity preservation and less overfitting. We release the source code of DVAR so that anyone can speed up their adaptation pipeline.

Faster customization of text-to-image models with DVAR

icon_post_23.svg

Text-to-image synthesis models like Stable Diffusion, DALL-E 2 or Imagen have increased in popularity over the past few years. The research community keeps developing new approaches, with RAPHAEL, DeepFloyd and DALL-E 3 being some of the most recent ones. Still, assessing the language understanding capabilities of such models remains a challenging problem. In our latest work, "Hypernymy Understanding Evaluation of Text-to-image Models via WordNet Hierarchy", we present a method for analyzing the linguistic abilities and world knowledge of text-to-image models by measuring how well they understand subtype relations between concepts.

Follow the cutting-edge research in computer science

Blog

Publications

DeDrift: Robust Similarity Search under Content Drift

TabDDPM: Modelling Tabular Data with Diffusion Models

SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient

FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU