Zobrazeno 1 - 10
of 17 588
pro vyhledávání: '"Anagnostopoulos, A"'
In this paper we propose a methodology combining Federated Learning (FL) with Cross-view Image Geo-localization (CVGL) techniques. We address the challenges of data privacy and heterogeneity in autonomous vehicle environments by proposing a personali
Externí odkaz:
http://arxiv.org/abs/2411.04692
This paper proposes a novel localization framework based on collaborative training or federated learning paradigm, for highly accurate localization of autonomous vehicles. More specifically, we build on the standard approach of KalmanNet, a recurrent
Externí odkaz:
http://arxiv.org/abs/2411.05847
Autor:
Eckhoff, Maren, Selimi, Valmir, Aranovitch, Alexander, Lyons, Ian, Briggs, Emily, Hou, Jennifer, Devereson, Alex, Macak, Matej, Champagne, David, Anagnostopoulos, Chris
Many therapies are effective in treating multiple diseases. We present an approach that leverages methods developed in natural language processing and real-world data to prioritize potential, new indications for a mechanism of action (MoA). We specif
Externí odkaz:
http://arxiv.org/abs/2410.19174
Autor:
Rigas, Spyros, Papachristou, Michalis, Papadopoulos, Theofilos, Anagnostopoulos, Fotios, Alexandridis, Georgios
Physics-Informed Neural Networks (PINNs) have emerged as a robust framework for solving Partial Differential Equations (PDEs) by approximating their solutions via neural networks and imposing physics-based constraints on the loss function. Traditiona
Externí odkaz:
http://arxiv.org/abs/2407.17611
Autor:
Hirasawa, Mitsuaki, Anagnostopoulos, Konstantinos N., Azuma, Takehiro, Hatakeyama, Kohta, Nishimura, Jun, Papadoudis, Stratos, Tsuchiya, Asato
The Lorentzian type IIB matrix model is a promising candidate for a nonperturbative formulation of superstring theory. Recently we performed complex Langevin simulations by adding a Lorentz invariant mass term as an IR regulator and found a (1+1)-dim
Externí odkaz:
http://arxiv.org/abs/2407.03491
Graph neural networks (GNNs) excel in learning from network-like data but often lack interpretability, making their application challenging in domains requiring transparent decision-making. We propose the Graph Kolmogorov-Arnold Network (GKAN), a nov
Externí odkaz:
http://arxiv.org/abs/2406.18354
Autor:
Singh, Simranjit, Fore, Michael, Karatzas, Andreas, Lee, Chaehong, Jian, Yanan, Shangguan, Longfei, Yu, Fuxun, Anagnostopoulos, Iraklis, Stamoulis, Dimitrios
As Large Language Models (LLMs) broaden their capabilities to manage thousands of API calls, they are confronted with complex data operations across vast datasets with significant overhead to the underlying system. In this work, we introduce LLM-dCac
Externí odkaz:
http://arxiv.org/abs/2406.06799
Autor:
Singh, Simranjit, Karatzas, Andreas, Fore, Michael, Anagnostopoulos, Iraklis, Stamoulis, Dimitrios
State-of-the-art sequential reasoning in Large Language Models (LLMs) has expanded the capabilities of Copilots beyond conversational tasks to complex function calling, managing thousands of API calls. However, the tendency of compositional prompting
Externí odkaz:
http://arxiv.org/abs/2405.17438
Autor:
Egger, Maximilian K., Ma, Wenyue, Mottin, Davide, Karras, Panagiotis, Bordino, Ilaria, Gullo, Francesco, Anagnostopoulos, Aris
Can we assess a priori how well a knowledge graph embedding will perform on a specific downstream task and in a specific part of the knowledge graph? Knowledge graph embeddings (KGEs) represent entities (e.g., "da Vinci," "Mona Lisa") and relationshi
Externí odkaz:
http://arxiv.org/abs/2404.16572
Decentralized Federated Learning (DFL) has become popular due to its robustness and avoidance of centralized coordination. In this paradigm, clients actively engage in training by exchanging models with their networked neighbors. However, DFL introdu
Externí odkaz:
http://arxiv.org/abs/2404.15943