?
Ensemble Distribution Distillation
.
Malinin A., Mlodozeniec B., Gales M.
Ivan Bulychev, Savchenko A., AI 2026 Vol. 7 No. 9 Article 380
Recent advances in large language model (LLM) agents have shown promise for autonomous decision-making in recommender systems. However, existing approaches suffer from two fundamental limitations: flat agent memories that conflate different information modalities and prohibitive computational costs that prevent scaling beyond a few hundred users. We propose Hybrid-GraphRAG, a recommender system that integrates hierarchical agent ...
Added: September 24, 2026
Лукьянов К. С., Перминов А. И., Turdakov D. Y. et al., / Series Computer Science "arxiv.org". 2024.
The vulnerability of artificial neural networks to adversarial perturbations in the black-box setting is widely studied in the literature. The majority of attack methods to construct these perturbations suffer from an impractically large number of queries required to find an adversarial example. In this work, we focus on knowledge distillation as an approach to conduct ...
Added: September 14, 2026
Severin N., Kartushov D., Urzhumov V. et al., , in: Advances in Information Retrieval: 48th European Conference on Information Retrieval, ECIR 2026, Delft, The Netherlands, March 29 – April 2, 2026, Proceedings, Part II. (LNCS, volume 16484).: Cham: Springer Publishing Company, 2026. P. 508–517.
Sequential recommender systems have achieved significant success in modeling temporal user behavior but remain limited in cap-turing rich user semantics beyond interaction patterns. Large Language Models (LLMs) present opportunities to enhance user understanding with their reasoning capabilities, yet existing integration approaches cre-ate prohibitive inference costs in real time. To address these limitations, we present a ...
Added: June 18, 2026
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
Sadrtdinov I., Dmitrii Pozdeev, Dmitry P Vetrov et al., , in: Advances in Neural Information Processing Systems 36 (NeurIPS 2023).: Curran Associates, Inc., 2023. P. 15936–15964.
Transfer learning and ensembling are two popular techniques for improving the performance and robustness of neural networks. Due to the high cost of pre-training, ensembles of models fine-tuned from a single pre-trained checkpoint are often used in practice. Such models end up in the same basin of the loss landscape, which we call the pre-train ...
Added: February 26, 2024
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
Malinin A., Gales M., , in: Advances in Neural Information Processing Systems 32 (NeurIPS 2019).: [б.и.], 2019.
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
Ryabinin M., Malinin A., Gales M., , in: Advances in Neural Information Processing Systems 34 (NeurIPS 2021).: Curran Associates, Inc., 2021. P. 6023–6035.
Added: October 31, 2021
Anna Beketova, Makarov I., , in: Advances in Computational Intelligence: 16th International Work-Conference on Artificial Neural Networks, IWANN 2021, Virtual Event, June 16–18, 2021, Proceedings, Part II.: Cham: Springer, 2021. Ch. 3 P. 28–42.
*Реализация соц. сети Instagram запрещена на территории России по основаниям осуществления экстремистской деятельности.
Instagram is one of the most popular photos sharing services. For more convenient content search people use hashtags (#nature, #love, etc.) in posts with photos. The author’s aim is to make hashtag prediction possible and convenient for users.
The paper provides a reader with ...
Added: September 1, 2021
Lobacheva E., Chirkova N., Kodryan M. et al., , in: Advances in Neural Information Processing Systems 33 (NeurIPS 2020).: Curran Associates, Inc., 2020. P. 2375–2385.
Added: October 29, 2020
Ashukha A., Vetrov D., Molchanov D. et al., , in: Workshop of the 6th International Conference on Learning Representations (ICLR).: International Conference on Learning Representations, ICLR, 2018. P. 1–6.
In this work, we investigate Batch Normalization technique and propose its probabilistic interpretation. We propose a probabilistic model and show that Batch Normalization maximazes the lower bound of its marginalized log-likelihood. Then, according to the new probabilistic model, we design an algorithm which acts consistently during train and test. However, inference becomes computationally inefficient. To ...
Added: October 31, 2018
Breyman A., Яковлев И. А., Прикаспийский журнал: управление и высокие технологии 2014 № 1 (25) С. 102–112
Optical recognition of text documents is inevitably error-prone process. To identify and correct that errors systems use post-processing techniques that are usually based on dictionary search. Using dictionaries can bring an acceptable quality of recognition for Latin, Cyrillic and other phonetic alphabets, but of little use for the languages in which the selection of individual ...
Added: February 27, 2014