Publications (30)
Statistical estimation of the Kullback-Leibler divergence
Alexander Bulinski, Denis Dimitrov
Wide conditions are provided to guarantee asymptotic unbiasedness and L^2-consistency of the introduced estimates of the Kullback-Leibler divergence for probability measures in R^d…
Your Transformer is Secretly Linear
Anton Razzhigaev, Matvey Mikhalchuk, Elizaveta Goncharova +4
This paper reveals a novel linear characteristic exclusive to transformer decoders, including models such as GPT, LLaMA, OPT, BLOOM and others. We analyze embedding transformations…
A new face swap method for image and video domains: a technical report
Daniil Chesakov, Anastasia Maltseva, Alexander Groshev +2
Deep fake technology became a hot field of research in the last few years. Researchers investigate sophisticated Generative Adversarial Networks (GAN), autoencoders, and other appr…
Unleashing the power of novel conditional generative approaches for new materials discovery
Lev Novitskiy, Vladimir Lazarev, Mikhail Tiutiulnikov +6
For a very long time, computational approaches to the design of new materials have relied on an iterative process of finding a candidate material and modeling its properties. AI ha…
Eco2AI: carbon emissions tracking of machine learning models as the first step towards sustainable AI
Semen Budennyy, Vladimir Lazarev, Nikita Zakharenko +9
The size and complexity of deep neural networks continue to grow exponentially, significantly increasing energy consumption for training and inference by these models. We introduce…
VIVAT: Virtuous Improving VAE Training through Artifact Mitigation
Lev Novitskiy, Viacheslav Vasilev, Maria Kovaleva +2
Variational Autoencoders (VAEs) remain a cornerstone of generative computer vision, yet their training is often plagued by artifacts that degrade reconstruction and generation qual…