Alexander Demidovskiy

According to our database, Alexander Demidovskiy authored at least 12 papers between 2016 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Hebb-Inspired Low Rank Adapters for Large Language Models Fine-Tuning.

Alexander Demidovskij, Artyom Tugaryov, Igor Salnikov, Olga Frolova, Aleksei Trutnev, Pengcheng Xie, Irina Novikova, Egor Zharikov, Vasilisa Blyudova, Yuri Ignatiev

Proceedings of the PRICAI 2025: Trends in Artificial Intelligence, 2025

Going Beyond LoRA Fine-Tuning with Hebb Learning: Blazingly Fast and Accurate.

Alexander Demidovskij, Igor Salnikov, Olga Frolova, Aleksei Trutnev, Artyom Tugaryov, Yuri Ignatiev, Vasilisa Blyudova, Egor Zharikov, Irina Novikova

Proceedings of the ECAI 2025 - 28th European Conference on Artificial Intelligence, 25-30 October 2025, Bologna, Italy, 2025

On the Influence of Layer Importance on LLM Fine-Tuning Acceleration and Quality.

Alexander Demidovskij, Irina Novikova, Artyom Tugaryov, Vasilisa Blyudova, Olga Frolova, Yuri Ignatiev, Igor Salnikov, Aleksei Trutnev, Egor Zharikov

Proceedings of the ECAI 2025 - 28th European Conference on Artificial Intelligence, 25-30 October 2025, Bologna, Italy, 2025

2024

ALOE: Boosting Large Language Model Fine-Tuning with Aggressive Loss-Based Elimination of Samples.

Alexander Demidovskij, Aleksei Trutnev, Artyom Tugaryov, Igor Salnikov

Proceedings of the ECAI 2024 - 27th European Conference on Artificial Intelligence, 19-24 October 2024, Santiago de Compostela, Spain, 2024

2023

Designing Sustainable Digitalization: Crisisology-Based Tradeoff Optimization in Sociotechnical Systems.

Sergey V. Zykov, Eduard Babkin, Boris Ulitin, Alexander Demidovskiy

Proceedings of the Intelligent Decision Technologies, 2023

2020

Designing a Neural Network Primitive for Conditional Structural Transformations.

Alexander Demidovskij, Eduard Babkin

Proceedings of the Artificial Intelligence - 18th Russian Conference, 2020

Effective Post-Training Quantization Of Neural Networks For Inference on Low Power Neural Accelerator.

Alexander Demidovskij, Eugene Smirnov

Proceedings of the 2020 International Joint Conference on Neural Networks, 2020

OpenVINO Deep Learning Workbench: A Platform for Model Optimization, Analysis and Deployment.

Alexander Demidovskij, Artyom Tugaryov, Alexander Suvorov, Yaroslav Tarkan, Marat Fatekhov, Igor Salnikov, Andrey Kashchikhin, Vladimir Golubenko, Galina Dedyukhina, Alina Alborova, Ryan Palmer, Mikhail Fedorov, Yury Gorbachev

Proceedings of the 32nd IEEE International Conference on Tools with Artificial Intelligence, 2020

2019

Implementation Aspects of Tensor Product Variable Binding in Connectionist Systems.

Alexander Demidovskij

Proceedings of the Intelligent Systems and Applications, 2019

2018

Hybrid neural network and bi-criteria tabu-machine: comparison of new approaches to maximum clique problem.

Eduard Babkin, Tatiana Babkina, Alexander Demidovskij

Int. J. Big Data Intell., 2018

2017

Development of a Model to Predict Intention Using Deep Learning.

Nikolay Karpov, Alexander Demidovskij, Alexey Malafeev

Proceedings of the Supplementary Proceedings of the Sixth International Conference on Analysis of Images, Social Networks and Texts (AIST 2017), Moscow, Russia, July 27, 2017

2016

Evolvable Semantic Platform for Facilitating Knowledge Exchange.

Nikolay Karpov, Eduard Babkin, Alexander Demidovskij

Proceedings of the Supplementary Proceedings of the Fifth International Conference on Analysis of Images, 2016