Zobrazeno 1 - 10
of 25 035
pro vyhledávání: '"Saba, P"'
Aiming for a greener transportation future, this study introduces an innovative control system for plug-in hybrid electric vehicles (PHEVs) that utilizes machine learning (ML) techniques to forecast energy usage in the pure electric mode of the vehic
Externí odkaz:
http://arxiv.org/abs/2412.09499
Autor:
Koukounas, Andreas, Mastrapas, Georgios, Wang, Bo, Akram, Mohammad Kalim, Eslami, Sedigheh, Günther, Michael, Mohr, Isabelle, Sturua, Saba, Martens, Scott, Wang, Nan, Xiao, Han
Contrastive Language-Image Pretraining (CLIP) is a highly effective method for aligning images and texts in a shared embedding space. These models are widely used for tasks such as cross-modal information retrieval and multi-modal understanding. Howe
Externí odkaz:
http://arxiv.org/abs/2412.08802
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by incorporating external, domain-specific data into the generative process. While LLMs are highly capable, they often rely on static, pre-trained datasets, limiting their abi
Externí odkaz:
http://arxiv.org/abs/2412.05838
Autor:
Memari, Mohammadali, Nejad, Soghra Mikaeyl, Rabiei, Amir Parsa, Eisaei, Mehrshad, Hesaraki, Saba
Multidomain sentiment analysis involves estimating the polarity of an unstructured text by exploiting domain specific information. One of the main issues common to the approaches discussed in the literature is their poor applicability to domains that
Externí odkaz:
http://arxiv.org/abs/2412.05591
Breast cancer stands as a prevalent cause of fatality among females on a global scale, with prompt detection playing a pivotal role in diminishing mortality rates. The utilization of ultrasound scans in the BUSI dataset for medical imagery pertaining
Externí odkaz:
http://arxiv.org/abs/2412.05585
Autor:
Akitaya, Hugo A., Fekete, Sándor P., Kramer, Peter, Molaei, Saba, Rieck, Christian, Stock, Frederick, Wallner, Tobias
We consider algorithmic problems motivated by modular robotic reconfiguration, for which we are given $n$ square-shaped modules (or robots) in a (labeled or unlabeled) start configuration and need to find a schedule of sliding moves to transform it i
Externí odkaz:
http://arxiv.org/abs/2412.05523
Autor:
Baraeinejad, Bardia, Forouzesh, Maryam, Babaei, Saba, Naghshbandi, Yasin, Torabi, Yasaman, Fazliani, Shabnam
In the last few decades, several wearable devices have been designed to monitor respiration rate in an effort to capture pulmonary signals with higher accuracy and reduce patients' discomfort during use. In this article, we present the design and imp
Externí odkaz:
http://arxiv.org/abs/2412.05405
Second-order methods are widely adopted to improve the convergence rate of learning algorithms. In federated learning (FL), these methods require the clients to share their local Hessian matrices with the parameter server (PS), which comes at a prohi
Externí odkaz:
http://arxiv.org/abs/2412.03867
Autor:
Francis, John, Esnaashari, Saba, Poletaev, Anton, Chakraborty, Sukankana, Hashem, Youmna, Bright, Jonathan
Large language models (LLMs) have demonstrated remarkable capabilities in text analysis tasks, yet their evaluation on complex, real-world applications remains challenging. We define a set of tasks, Multi-Insight Multi-Document Extraction (MIMDE) tas
Externí odkaz:
http://arxiv.org/abs/2411.19689
Autor:
Sritharan, Sivaguru S., Mudaliar, Saba
In this paper we study a large class of nonlinear stochastic wave equations that arise in laser generation models and models for propagation in random media in a unified mathematical framework. Continuous and pulse-wave propagation models, free elect
Externí odkaz:
http://arxiv.org/abs/2411.16013