Zobrazeno 1 - 10
of 32 051
pro vyhledávání: '"Rostami, A."'
Unsupervised Domain Adaptation (UDA) is crucial for reducing the need for extensive manual data annotation when training deep networks on point cloud data. A significant challenge of UDA lies in effectively bridging the domain gap. To tackle this cha
Externí odkaz:
http://arxiv.org/abs/2410.02720
Autor:
Rostami, M., Kia, S. S.
Federated learning (FL) has gained considerable popularity for distributed machine learning due to its ability to preserve the privacy of participating agents by eliminating the need for data aggregation. Nevertheless, communication costs between age
Externí odkaz:
http://arxiv.org/abs/2410.02260
Autor:
Ghasemi, S. Mojtaba, Rostami-Shirazi, Ali, Khalaj, Pouria, Zonoozi, Akram Hasani, Haghi, Hosein
We investigate the impact of primordial mass segregation on the formation and evolution of dark star clusters (DSCs). Considering a wide range of initial conditions, we conducted $N$-body simulations of globular clusters (GCs) around the Milky Way. I
Externí odkaz:
http://arxiv.org/abs/2409.15280
Backscatter communication (BC) emerges as a pivotal technology for ultra-low-power energy harvesting applications, but its practical deployment is often hampered by notable security vulnerabilities. Physical layer authentication (PLA) offers a promis
Externí odkaz:
http://arxiv.org/abs/2410.02778
Backscatter communication (BC) has emerged as a pivotal wireless communication paradigm owing to its low-power and cost-effective characteristics. However, BC faces various challenges from its low signal detection rate to its security vulnerabilities
Externí odkaz:
http://arxiv.org/abs/2410.01829
Theoretical Insights into Overparameterized Models in Multi-Task and Replay-Based Continual Learning
Multi-task learning (MTL) is a machine learning paradigm that aims to improve the generalization performance of a model on multiple related tasks by training it simultaneously on those tasks. Unlike MTL, where the model has instant access to the trai
Externí odkaz:
http://arxiv.org/abs/2408.16939
Backscattering tag-to-tag networks (BTTNs) represent a passive radio frequency identification (RFID) system that enables direct communication between tags within an external radio frequency (RF) field. However, low spectral efficiency and short-range
Externí odkaz:
http://arxiv.org/abs/2408.16853
Autor:
Ghadi, Farshad Rostami, Wong, Kai-Kit, Kaveh, Masoud, Lopez-Martinez, F. Javier, New, Wee Kiat, Xu, Hao
This paper examines the impact of emerging fluid antenna systems (FAS) on reconfigurable intelligent surface (RIS)-aided secure communications. Specifically, we consider a classic wiretap channel, where a fixed-antenna transmitter sends confidential
Externí odkaz:
http://arxiv.org/abs/2408.14969
Autor:
Cai, Yuliang, Rostami, Mohammad
Large vision-language models (VLMs) have shown significant performance boost in various application domains. However, adopting them to deal with several sequentially encountered tasks has been challenging because finetuning a VLM on a task normally l
Externí odkaz:
http://arxiv.org/abs/2408.11742
Autor:
Ghadi, Farshad Rostami, Wong, Kai-Kit, Lopez-Martinez, F. Javier, Shin, Hyundong, Hanzo, Lajos
This paper investigates a two-user downlink system for integrated sensing and communication (ISAC) in which the two users deploy a fluid antenna system (FAS) and adopt the nonorthogonal multiple access (NOMA) strategy. Specifically, the integrated se
Externí odkaz:
http://arxiv.org/abs/2408.04724