?
Scaling Ensemble Distribution Distillation to Many Classes with Proxy Targets
P. 6023–6035.
Ryabinin M., Malinin A., Gales M.
In book
Curran Associates, Inc., 2021.
Aparin G., Popov Vadim, Sadekova T. et al., , in: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2026.: International Speech Communication Association, 2026. P. 631–640.
Whisper, a widely adopted ASR model, is known to suffer from hallucinations — coherent transcriptions generated for non-speech audio entirely disconnected from the input. We investigate whether hallucinations can be detected and mitigated through Whisper’s internal representations. We extract audio encoder activations and evaluate two representation spaces: raw Whisper activations and Sparse AutoEncoder (SAE) latents. ...
Added: October 6, 2026
International Speech Communication Association, 2026.
Added: October 6, 2026
Aleksei Samarin, Alexander Savelev, Aleksei Toropov et al., Optical Memory and Neural Networks (Information Optics) 2024 Vol. 33 P. S424–S434
This study explores the development of classifiers for microbial images, specifically focusing on streptococci captured via microscopy of live samples. Our approach uses AutoML-based techniques and automates the creation and analysis of feature spaces to produce optimal descriptors for classifying these microscopic images. This technique leverages interpretable taxonomic features based on the external geometric attributes ...
Added: September 21, 2026
Aleksei Samarin, Alexander Savelev, Aleksei Toropov et al., Pattern Recognition and Image Analysis 2025 Vol. 35 No. 2 P. 148–158
This paper describes our research on creating classifiers for microbial images (micrococci microscopy images) obtained from pictures of unfixed microscopic scenes. In our work, we propose an AutoML approach based on the automatic generation and analysis of the feature space for constructing the most optimal descriptors of microorganism images for subsequent classification. This makes it ...
Added: September 19, 2026
Aleksei Samarin, Alexander Savelev, Aleksei Toropov et al., Pattern Recognition and Image Analysis 2026 Vol. 36 No. 2 P. 302–312
The lack of annotated microscopic datasets remains a major obstacle to training robust deep learning models for microbial classification. In this paper, a novel data augmentation pipeline that uses visual–linguistic large-scale models to generate synthetic microscopic images of six different bacterial and nonbacterial classes has been proposed. Synthetic samples have gradually been added to the ...
Added: September 19, 2026
Aleksei Samarin, Aleksei Toropov, Kotenko E. et al., , in: Proceedings of the 37th Conference of Open Innovations Association FRUCT, Helsinki, Finland, 14-16 May 2025, Issue 1 (Full Papers)Vol. 37.: Helsinki: FRUCT Oy, 2025. P. 278–284.
This study introduces an innovative method for recognizing automatically generated images by utilizing adapted descriptors specifically designed to analyze unique structural and morphological features characteristic of artificially created content. The methodology focuses on analyzing features inherent to image generation processes, ensuring the optimization of descriptors for identifying complex and subtle patterns associated with generative algorithms. ...
Added: September 19, 2026
Golyadkin M., Innokentiy Humonen, Rubanova V. et al., , in: MM '25: Proceedings of the 33rd ACM International Conference on Multimedia.: Association for Computing Machinery (ACM), 2025. P. 12875–12881.
We present the first multimodal dataset MuMMy, for developing research assistants that can interpret Egyptian hieroglyphic texts. It pairs images with Gardiner codes, transliteration, and English translation at two levels of granularity. We also evaluate several deep learning pipelines across OCR, transliteration, and translation tasks, revealing the complexity of the domain and the challenges posed ...
Added: November 8, 2025
Moiseev N., Абрамов И. А., Камакин А. Ю., В кн.: Параллельные вычислительные технологии – XIX всероссийская конференция с международным участием, ПаВТ'2025, г. Москва, 8–10 апреля 2025 г. Короткие статьи и описания плакатов.: Челябинск: Издательский центр ЮУрГУ, 2025. С. 301–301.
In recent years, with the advancement of deep learning and neural network methods, their application in geospatial analysis tasks has become particularly relevant. A key challenge in this field is assessing the state of urban infrastructure, including the classification of buildings by their functional purpose (residential, commercial, governmental, industrial). The use of neural networks significantly ...
Added: September 17, 2025
Fadeeva E., Vashurin R., Tsvigun A. et al., , in: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing.: Singapore: Association for Computational Linguistics, 2023. P. 446 –461.
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 facts without providing users an apparent means to discern the veracity of their statements. Uncertainty estimation (UE) methods are one ...
Added: February 17, 2025
Tatiana Sherstinova, Nikolay Mikhaylovskiy, Evgenia Kolpashchikova et al., , in: Proceedings of the 35th Conference of Open Innovations Association FRUCT, 24-26 April 2024, Tampere, FinlandIssue 1.: FRUCT Oy, 2024. P. 253–258.
Contemporary advancements in NLP and neural network techniques are paving the way to enhance and harness traditional linguistic resources and corpora, as well as expand the methods of applying neural networks for complex language material. Thus, a weak point for both theoretical and applied linguistic tasks is the processing of spontaneous everyday speech. Two experiments ...
Added: November 29, 2024
Sobyanin K., Kulikova S., Информатика и автоматизация (Труды СПИИРАН) 2024 Т. 23 № 4 С. 1022–1046
The problem of training deep neural networks on small samples is especially relevant for medical problems. The paper examines the impact of pixel-wise marking of significant objects in the image, over the true class label, on the quality of the classification. To achieve better classification results on small samples, we propose a multitasking architecture -- ...
Added: June 29, 2024
Shuranov E., / Series Computer Science "arxiv.org". 2021.
Text encodings from automatic speech recognition (ASR) transcripts and audio representations have shown promise in speech emotion recognition (SER) ever since. Yet, it is challenging to explain the effect of each information stream on the SER systems. Further, more clarification is required for analysing the impact of ASR's word error rate (WER) on linguistic emotion ...
Added: February 14, 2023
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
Copenhagen, Denmark: CEUR Workshop Proceedings, 2021.
The second workshop on Crowd Science is organized in conjunction with the 47th International Conference on Very Large Data Bases (VLDB 2021). This workshop is the second in a series of events that has the goal of helping crowdsourcing “transition” from art to science, and tackles the research challenges that we face to make crowdsourcing ...
Added: December 13, 2021
Плетенев С. А., В кн.: Компьютерная лингвистика и интеллектуальные технологии: По материалам ежегодной международной конференции «Диалог» (Москва, 16–19 июня 2021 г.)Issue 20.: Russian State University for the Humanitie, 2021.
Added: December 13, 2021
Malinin A., Gales M., , in: Advances in Neural Information Processing Systems 32 (NeurIPS 2019).: [б.и.], 2019.
Added: November 1, 2021
Malinin A., Mlodozeniec B., Gales M., , in: Proceedings of the 8th International Conference on Learning Representations (ICLR 2020).: ICLR, 2020.
Added: November 1, 2021
Andrey Malinin, Gales M., , in: Proceedings of the 9th International Conference on Learning Representations (ICLR 2021). ICLR, 2021.: ICLR, 2021. P. 1–31.
Added: November 1, 2021