Skip to content

Viktoria Chekalina

Publication record assembled from the DBLP archive of ranked conferences.

Papers indexed

7

Venues

5

Active years

2021–2026

Best venue rank

A*

Where they publish

Papers

7 indexed papers, newest first.

YearVenueTitleAuthors
2026EACLAcceleration of Backpropagation in Linear Layers of Transformer Models Based on Gradient Structure.Dmitrii Topchii, Alexander Panchenko, Viktoria Chekalina
2024EMNLPSparseGrad: A Selective Method for Efficient Fine-tuning of MLP Layers.Viktoria Chekalina, Anna Rudenko, Gleb Mezentsev, Aleksandr Mikhalev, Alexander Panchenko, Ivan V. Oseledets
2023AISTTransformers Compression: A Study of Matrix Decomposition Methods Using Fisher Information.Sergey Pletenev, Daniil Moskovskiy, Viktoria Chekalina, Mikhail Seleznyov, Sergey Zagoruyko, Alexander Panchenko
2023PACLICEfficient GPT Model Pre-training using Tensor Train Matrix Representation.Viktoria Chekalina, Georgiy Novikov, Julia Gusak, Alexander Panchenko, Ivan V. Oseledets
2023PACLICA Computational Study of Matrix Decomposition Methods for Compression of Pre-trained Transformers.Sergey Pletenev, Viktoria Chekalina, Daniil Moskovskiy, Mikhail Seleznev, Sergey Zagoruyko, Alexander Panchenko
2022ACLMEKER: Memory Efficient Knowledge Embedding Representation for Link Prediction and Question Answering.Viktoria Chekalina, Anton Razzhigaev, Albert Sayapin, Evgeny Frolov, Alexander Panchenko
2021EACLWhich is Better for Deep Learning: Python or MATLAB? Answering Comparative Questions in Natural Language.Viktoria Chekalina, Alexander Bondarenko, Chris Biemann, Meriem Beloucif, Varvara Logacheva, Alexander Panchenko