Three 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).

Papers accepted to ICML 2024

We are excited to present our array of educational courses designed by our researchers. We recently introduced a graph-based machine learning course at the Yandex School of Data Analysis. Additionally, we offer diverse programs in collaboration with partner universities and other research groups. 

Discover cutting-edge learning with Yandex Research

Today, we present the YaART: Yet Another ART Rendering Technology paper. YaART is our production-grade text-to-image cascaded diffusion model aligned to human preferences using Reinforcement Learning from Human Feedback (RLHF). 

YaART pre-print is released

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

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.

Tabular data

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

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

Generative models

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

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.

Neural algorithmic reasoning

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

Computer vision

icon_post_8.svg

In this work, we achieve perfect neural execution of several algorithms by forcing the node and edge representations to be from a fixed finite set. Also, the proposed architectural choice allows us to prove the correctness of the learned algorithms for any test data.

Discrete neural algorithmic reasoning

icon_post_28.svg


We introduce SpecExec, a speculative decoding method that delivers up to 20 tokens per iteration and up to 15x speedups in offloading settings. This enables usable LLM inference speeds for users with limited GPU VRAM sizes, who have had to use offloading or settle for lower quality models until now. 

SpecExec: Massively Parallel Speculative Decoding for Interactive LLM Inference on Consumer Devices

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.

Follow the cutting-edge research in computer science

Blog

Publications

Extreme Compression of Large Language Models via Additive Quantization

Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features

Zero-Sum Positional Differential Games as a Framework for Robust Reinforcement Learning: Deep Q-Learning Approach

Your Student is Better Than Expected: Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion Models