272 citations · 742 across the 36 of their papers we have counts for
7 papers · 1 filter
Friction-Augmented Drifting Models for Resource-Efficient Domain Translation
Arkadii Kazanskii, Tatiana Petrova, Andrey Ustyuzhanin +3
Single-step generators promise high-fidelity synthesis at a fraction of the inference and training cost of ordinary differential equation (ODE)-based flow models, a central concern…
MiAD: Mirage Atom Diffusion for De Novo Crystal Generation
Andrey Okhotin, Maksim Nakhodnov, Nikita Kazeev +3
In recent years, diffusion-based models have demonstrated exceptional performance in searching for simultaneously stable, unique, and novel (S.U.N.) crystalline materials. However,…
Linguacodus: A Synergistic Framework for Transformative Code Generation in Machine Learning Pipelines
Ekaterina Trofimova, Emil Sataev, Andrey E. Ustyuzhanin
In the ever-evolving landscape of machine learning, seamless translation of natural language descriptions into executable code remains a formidable challenge. This paper introduces…
The Tracking Machine Learning challenge : Throughput phase
Sabrina Amrouche, Laurent Basara, Paolo Calafiura +18
This paper reports on the second "Throughput" phase of the Tracking Machine Learning (TrackML) challenge on the Codalab platform. As in the first "Accuracy" phase, the participants…
Black-Box Optimization with Local Generative Surrogates
Sergey Shirobokov, Vladislav Belavin, Michael Kagan +2
We propose a novel method for gradient-based optimization of black-box simulators using differentiable local surrogate models. In fields such as physics and engineering, many proce…
Generalization of Change-Point Detection in Time Series Data Based on Direct Density Ratio Estimation
Mikhail Hushchyn, Andrey Ustyuzhanin
The goal of the change-point detection is to discover changes of time series distribution. One of the state of the art approaches of the change-point detection are based on direct…