Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Bulatov, Aydar"'
Autor:
Churin, Igor, Apishev, Murat, Tikhonova, Maria, Shevelev, Denis, Bulatov, Aydar, Kuratov, Yuri, Averkiev, Sergej, Fenogenova, Alena
Recent advancements in Natural Language Processing (NLP) have fostered the development of Large Language Models (LLMs) that can solve an immense variety of tasks. One of the key aspects of their application is their ability to work with long text doc
Externí odkaz:
http://arxiv.org/abs/2408.02439
This paper addresses the challenge of creating a neural architecture for very long sequences that requires constant time for processing new information at each time step. Our approach, Associative Recurrent Memory Transformer (ARMT), is based on tran
Externí odkaz:
http://arxiv.org/abs/2407.04841
Autor:
Kuratov, Yuri, Bulatov, Aydar, Anokhin, Petr, Rodkin, Ivan, Sorokin, Dmitry, Sorokin, Artyom, Burtsev, Mikhail
In recent years, the input context sizes of large language models (LLMs) have increased dramatically. However, existing evaluation methods have not kept pace, failing to comprehensively assess the efficiency of models in handling long contexts. To br
Externí odkaz:
http://arxiv.org/abs/2406.10149
Autor:
Kuratov, Yuri, Bulatov, Aydar, Anokhin, Petr, Sorokin, Dmitry, Sorokin, Artyom, Burtsev, Mikhail
This paper addresses the challenge of processing long documents using generative transformer models. To evaluate different approaches, we introduce BABILong, a new benchmark designed to assess model capabilities in extracting and processing distribut
Externí odkaz:
http://arxiv.org/abs/2402.10790
Real-world Knowledge Graphs (KGs) often suffer from incompleteness, which limits their potential performance. Knowledge Graph Completion (KGC) techniques aim to address this issue. However, traditional KGC methods are computationally intensive and im
Externí odkaz:
http://arxiv.org/abs/2311.01326
A major limitation for the broader scope of problems solvable by transformers is the quadratic scaling of computational complexity with input size. In this study, we investigate the recurrent memory augmentation of pre-trained transformer models to e
Externí odkaz:
http://arxiv.org/abs/2304.11062
Transformer-based models show their effectiveness across multiple domains and tasks. The self-attention allows to combine information from all sequence elements into context-aware representations. However, global and local information has to be store
Externí odkaz:
http://arxiv.org/abs/2207.06881