Zobrazeno 1 - 10
of 789
pro vyhledávání: '"A A, Petrakov"'
Autor:
Vashurin, Roman, Fadeeva, Ekaterina, Vazhentsev, Artem, Tsvigun, Akim, Vasilev, Daniil, Xing, Rui, Sadallah, Abdelrahman Boda, Rvanova, Lyudmila, Petrakov, Sergey, Panchenko, Alexander, Baldwin, Timothy, Nakov, Preslav, Panov, Maxim, Shelmanov, Artem
Uncertainty quantification (UQ) is becoming increasingly recognized as a critical component of applications that rely on machine learning (ML). The rapid proliferation of large language models (LLMs) has stimulated researchers to seek efficient and e
Externí odkaz:
http://arxiv.org/abs/2406.15627
Autor:
Rykov, Elisei, Shishkina, Yana, Petrushina, Kseniia, Titova, Kseniia, Petrakov, Sergey, Panchenko, Alexander
In this paper, we present our novel systems developed for the SemEval-2024 hallucination detection task. Our investigation spans a range of strategies to compare model predictions with reference standards, encompassing diverse baselines, the refineme
Externí odkaz:
http://arxiv.org/abs/2404.06137
Autor:
Fadeeva, Ekaterina, Rubashevskii, Aleksandr, Shelmanov, Artem, Petrakov, Sergey, Li, Haonan, Mubarak, Hamdy, Tsymbalov, Evgenii, Kuzmin, Gleb, Panchenko, Alexander, Baldwin, Timothy, Nakov, Preslav, Panov, Maxim
Large language models (LLMs) are notorious for hallucinating, i.e., producing erroneous claims in their output. Such hallucinations can be dangerous, as occasional factual inaccuracies in the generated text might be obscured by the rest of the output
Externí odkaz:
http://arxiv.org/abs/2403.04696
Autor:
Fadeeva, Ekaterina, Vashurin, Roman, Tsvigun, Akim, Vazhentsev, Artem, Petrakov, Sergey, Fedyanin, Kirill, Vasilev, Daniil, Goncharova, Elizaveta, Panchenko, Alexander, Panov, Maxim, Baldwin, Timothy, Shelmanov, Artem
Recent advancements in the capabilities of large language models (LLMs) have paved the way for a myriad of groundbreaking applications in various fields. However, a significant challenge arises as these models often "hallucinate", i.e., fabricate fac
Externí odkaz:
http://arxiv.org/abs/2311.07383
Transformer-based neural network architectures achieve state-of-the-art results in different domains, from natural language processing (NLP) to computer vision (CV). The key idea of Transformers, the attention mechanism, has already led to significan
Externí odkaz:
http://arxiv.org/abs/2212.14246
Publikováno v:
IEEE Access, Vol 12, Pp 97833-97850 (2024)
The attention-based models are widely used for time series data. However, due to the quadratic complexity of attention regarding input sequence length, the application of Transformers is limited by high resource demands. Moreover, their modifications
Externí odkaz:
https://doaj.org/article/1989c8f907cb49688b80ff5798f2ba28
Autor:
A. I. Petrakov, V. V. Sheikin, S. V. Krivoshchekov, E. A. Bezverkhniaia, A. M. Guryev, M. V. Belousov
Publikováno v:
Разработка и регистрация лекарственных средств, Vol 12, Iss 4, Pp 189-196 (2023)
Introduction. Cytochromes P450 depression is the reason for the low effectiveness of etiotropic and pathogenetic therapy of hepatitis. Recent experimental and clinical studies demonstrated the need for use of inducers of hepatocytes monooxygenase sys
Externí odkaz:
https://doaj.org/article/f41a52d7ca7b4ec8a30996491e5e30e3
Autor:
Yury Petrakov, Yan Romanov
Publikováno v:
Mechanics and Advanced Technologies, Vol 7, Iss 1 (97), Pp 51-60 (2023)
Contour milling is characterized by quasi-stationary, which leads to the occurrence of a machining error caused by elastic deflections of the machining system. Moreover, such an error cannot be eliminated by sub-adjusting the control program "for siz
Externí odkaz:
https://doaj.org/article/4a8b0a72e0fa459c9414e345d423cdc5
Autor:
Yuri Petrakov, Mariia Danylchenko
Publikováno v:
Mechanics and Advanced Technologies, Vol 7, Iss 2 (98) (2023)
Due to structural limitations, the processes of boring holes are performed in a low-rigidity machining system, which predetermines their susceptibility to vibrations. The article is devoted to the study of the process of boring holes on CNC machines,
Externí odkaz:
https://doaj.org/article/0266c4029ca947f6b0b63f62e613f6a4
Autor:
Aghaei, Hamed, Penkov, Grigory M., Solomoichenko, Dmitry A., Toorajipour, Ali, Petrakov, Dmitry G., Jafarpour, Hamed, Ghosh, Sayantan
Publikováno v:
In Ultrasonics July 2023 132