?
Transformers: “The End of History” for Natural Language Processing?
P. 677–693.
Publication based on the results of:
Makarov N., Savchenko A., Zemtsova I. et al., Scientific Reports 2025 Vol. 15 Article 26641
The grey wolf (Canis lupus) is a pivotal species for ecological studies. As a key participant in ecosystem
processes, it also serves as a model for investigating social structure formation and ecological
adaptation. However, the species’ complex social behavior, spatial dynamics, and expansive habitats
make monitoring and population assessments across large areas particularly challenging. In recent
years, audio traps ...
Added: June 16, 2026
Kristan M., Matas J., Tokmakov P. et al., , in: 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW).: Honolulu: IEEE, 2025. P. 7472–7490.
The VOTS2025 is the third edition of the Visual Object Tracking Segmentation benchmark. Organised the VOT initiative, VOTS builds on 10 years of experience in organising VOT challenges. Building on the tracking setup introduced in VOTS2023, the challenge continues to integrate short-term and long-term tracking, as well as single-target and multi-target scenarios, using segmentation masks ...
Added: May 3, 2026
Moshkin A., Лапутин Ф. А., Сидоров И. В., DIGITAL DIAGNOSTICS 2024 Т. 5 № S1 С. 40–42
BACKGROUND: Ovarian reserve reflects a woman's ability to successfully realize reproductive function. The assessment of ovarian reserve is an urgent task for clinical practice [1] and is important in scientific research. The use of computerized diagnostic image processing methods can accelerate and facilitate the performance of routine tasks in clinical practice. Their use in retrospective ...
Added: February 21, 2026
Arteaga Moreano B. D., Chervov N., Poptsova M., Scientific Reports 2026 Vol. 16 No. 1 Article 4772
Accurate prediction of protein-protein interactions (PPIs) is fundamental to understanding biological processes and disease mechanisms. While deep learning offers a powerful alternative to costly experimental methods, existing approaches often overlook critical protein-surface information and rely on simplistic feature fusion techniques, thereby limiting performance. To address this, we introduce GSMFormer-PPI, a novel multimodal framework that integrates ...
Added: February 4, 2026
Prikhodko R., Moshkin A., Romanov A., , in: 2025 International Russian Automation Conference (RusAutoCon).: IEEE, 2025. P. 273–278.
The vertebral arteries are one of the most important sources of blood supply to the brain, therefore any pathological changes in them can be the reason behind serious diseases. Magnetic Resonance Imaging (MRI) allows diagnosticians to examine main arteries, which is exceptionally important for effective diagnosis. However, because of the small size of arteries relative ...
Added: November 6, 2025
Арутюнов Г. А., Avdoshin S. M., Труды Института системного программирования РАН 2024 Т. 36 № 4 С. 69–80
Although software development is mostly a creative process, there are many scrutiny tasks. As in other industries, there is a trend for automation of routine work. In many cases, machine learning and neural networks have become a useful assistant in that matter. Programming is not an exception: GitHub has stated that Copilot is already used ...
Added: November 1, 2024
Edward Elgar Publishing, 2024.
As higher education continues to expand and an increasing number of graduates enter the workforce, this insightful book considers the crucial social and economic questions raised by this societal shift. Fátima Suleman, Pedro Videira and Pedro Teixeira bring together an array of experts to illustrate the connections between higher education and the labour market across ...
Added: August 15, 2024
Shirnin A., Andreev N., Potapova S. et al., IEEE/ACM Transactions on Speech and Language Processing 2024 Vol. 32 P. 2751–2763
We present an approach to evaluate the robustness of pre-trained vision and language (V&L) models to noise in input data. Given a source image/text, we perturb it using standard computer vision (CV) / natural language processing (NLP) techniques and feed it to a V&L model. To track performance changes, we explore the problem of visual ...
Added: July 19, 2024
Chistyakova K., Kazakova Tatiana, / NRU HSE. Series WP BRP "Linguistics". 2023. No. 115.
The problem of language models’ interpretation is extensively inspected, but no universal answers have been found. Our study offers to combine widely accepted probing methods with a novel approach to a neural network under investigation. We propose to break grammatical forms on the pre-training step in order to get two "sibling" models, as it casts ...
Added: November 29, 2023
Zaev R., Romanov A., Solovyev R., , in: 2023 International Russian Smart Industry Conference (SmartIndustryCon), 27-31 March 2023.: Sochi: IEEE, 2023. P. 460–465.
Medical research has made tremendous progress in detecting various pathologies in the human body. There is still the problem of the speed of the process, and the lack of a sufficient number of trained professionals in this field. Detection of prostate cancer, in particular, without surgery is a very labor- intensive process. A neural network-based ...
Added: July 30, 2023
Stepanyants V., Mantsa Andzhusheva, Romanov A., , in: 2023 International Russian Smart Industry Conference (SmartIndustryCon), 27-31 March 2023.: Sochi: IEEE, 2023. P. 621–626.
Many traffic accidents happen on the roads every day and a lot of them are captured on traffic or dashboard cameras. This data could be used to train machine learning models to predict dangerous situations so that they can be prevented. For that, it should be organized into datasets. Nowadays a limited amount of traffic ...
Added: July 30, 2023
Hardalov M., Chernyavskiy A., Koychev I. et al., , in: Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers).: Association for Computational Linguistics, 2022. P. 266–285.
While there has been substantial progress in developing systems to automate fact-checking, they still lack credibility in the eyes of the users. Thus, an interesting approach has emerged: to perform automatic fact-checking by verifying whether an input claim has been previously fact-checked by professional fact-checkers and to return back an article that explains their decision. ...
Added: May 21, 2023
Chernyavskiy A., Ilvovsky D., Kalinin P. et al., , in: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2022).: Association for Computational Linguistics, 2022. P. 116–126.
The use of contrastive loss for representation learning has become prominent in computer vision, and it is now getting attention in Natural Language Processing (NLP).Here, we explore the idea of using a batch-softmax contrastive loss when fine-tuning large-scale pre-trained transformer models to learn better task-specific sentence embeddings for pairwise sentence scoring tasks.We introduce and study ...
Added: October 4, 2022
Borzunov A., Ryabinin M., Dettmers T. et al., , in: Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track.: PMLR, 2022. P. 335–342.
Added: July 27, 2022
Association for Computational Linguistics, 2022.
Uncertainty estimation (UE) of model predictions is a crucial step for a variety of tasks such as active learning, misclassification detection, adversarial attack detection, out-of-distribution detection, etc. Most of the works on modeling the uncertainty of deep neural networks evaluate these methods on image classification tasks. Little attention has been paid to UE in natural ...
Added: May 17, 2022
Samenko I., Tikhonov A., Kozlovskii B. et al., / Series Computer Science "arxiv.org". 2021.
Transformers are responsible for the vast majority of recent advances in natural language processing. The majority of practical natural language processing applications of these models is typically enabled through transfer learning. This paper studies if corpus-specific tokenization used for fine-tuning improves the resulting performance of the model. Through a series of experiments, we demonstrate that ...
Added: January 17, 2022
Tikhonov A., Ryabinin M., , in: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021.: Association for Computational Linguistics, 2021. P. 3534–3546.
Added: September 30, 2021
Davletov A., Gordeev D., Nikolay Arefyev et al., , in: Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021).: Association for Computational Linguistics, 2021. P. 1249–1254.
This work describes our approach for subtasks of SemEval-2021 Task 8: MeasEval: Counts and Measurements which took the official first place in the competition. To solve all subtasks we use multi-task learning in a question-answering-like manner. We also use learnable scalar weights to weight subtasks’ contribution to the final loss in multi-task training. We fine-tune ...
Added: September 23, 2021
Lebedev A. V., Исраелян Е. А., Маркетинговые коммуникации 2021 № 02(114) С. 124–138
During the pandemic, health has become a core value. Grocery retailers realized the benefits of communicating with eco-consumers. The authors identified customer segments based on their attitude to healthy lifestyles. The article provides data on the gender and age structure of consumers with the average values of receipts, describes portraits of different types of eco-consumers ...
Added: June 10, 2021