Zobrazeno 1 - 10
of 1 127
pro vyhledávání: '"Lindenbaum, P"'
Multi-view representation learning (MvRL) has garnered substantial attention in recent years, driven by the increasing demand for applications that can effectively process and analyze data from multiple sources. In this context, graph Laplacian-based
Externí odkaz:
http://arxiv.org/abs/2411.02138
Effective spatio-temporal measurements of water surface elevation (water waves) in laboratory experiments are essential for scientific and engineering research. Existing techniques are often cumbersome, computationally heavy and generally suffer from
Externí odkaz:
http://arxiv.org/abs/2410.22849
Large Language Models (LLMs) have shown promise in highly-specialized domains, however challenges are still present in aspects of accuracy and costs. These limitations restrict the usage of existing models in domain-specific tasks. While fine-tuning
Externí odkaz:
http://arxiv.org/abs/2410.21479
Training and fine-tuning large language models (LLMs) come with challenges related to memory and computational requirements due to the increasing size of the model weights and the optimizer states. Various techniques have been developed to tackle the
Externí odkaz:
http://arxiv.org/abs/2410.17881
Effective spatio-temporal measurements of water surface elevation (water waves) in laboratory experiments are crucial for scientific and engineering research. Existing techniques are often cumbersome, computationally heavy and generally suffer from l
Externí odkaz:
http://arxiv.org/abs/2410.14988
Choosing a meaningful subset of features from high-dimensional observations in unsupervised settings can greatly enhance the accuracy of downstream analysis, such as clustering or dimensionality reduction, and provide valuable insights into the sourc
Externí odkaz:
http://arxiv.org/abs/2407.09061
The phenomenon of double descent has recently gained attention in supervised learning. It challenges the conventional wisdom of the bias-variance trade-off by showcasing a surprising behavior. As the complexity of the model increases, the test error
Externí odkaz:
http://arxiv.org/abs/2406.11703
Large Language Models (LLMs) can become outdated over time as they may lack updated world knowledge, leading to factual knowledge errors and gaps. Knowledge Editing (KE) aims to overcome this challenge using weight updates that do not require expensi
Externí odkaz:
http://arxiv.org/abs/2406.09920
With the increasing prevalence of voice-activated devices and applications, keyword spotting (KWS) models enable users to interact with technology hands-free, enhancing convenience and accessibility in various contexts. Deploying KWS models on edge d
Externí odkaz:
http://arxiv.org/abs/2406.06634
Standard convolutions are prevalent in image processing and deep learning, but their fixed kernel design limits adaptability. Several deformation strategies of the reference kernel grid have been proposed. Yet, they lack a unified theoretical framewo
Externí odkaz:
http://arxiv.org/abs/2406.05400