Zobrazeno 1 - 10
of 4 048
pro vyhledávání: '"Ranasinghe, P."'
We propose a novel flexible and scalable framework to design integrated communication and computing (ICC) -- a.k.a. over-the-air computing (AirComp)-- receivers. To elaborate, while related literature so far has generally focused either on theoretica
Externí odkaz:
http://arxiv.org/abs/2411.02016
Sarcasm is a rhetorical device that is used to convey the opposite of the literal meaning of an utterance. Sarcasm is widely used on social media and other forms of computer-mediated communication motivating the use of computational models to identif
Externí odkaz:
http://arxiv.org/abs/2410.18882
Autonomous aerial vehicles can provide efficient and effective solutions for radio frequency (RF) source tracking and localizing problems with applications ranging from wildlife conservation to search and rescue operations. Existing lightweight, low-
Externí odkaz:
http://arxiv.org/abs/2410.13081
Autor:
Ranasinghe, Kuranage Roche Rayan, Ge, Yao, de Abreu, Giuseppe Thadeu Freitas, Guan, Yong Liang
In this paper, we propose a novel low complexity time domain (TD) oversampling receiver framework under affine frequency division multiplexing (AFDM) waveforms for joint channel estimation and data detection (JCEDD). Leveraging a generalized doubly-d
Externí odkaz:
http://arxiv.org/abs/2410.05088
Autor:
Qian, Shenbin, Sindhujan, Archchana, Kabra, Minnie, Kanojia, Diptesh, Orăsan, Constantin, Ranasinghe, Tharindu, Blain, Frédéric
Leveraging large language models (LLMs) for various natural language processing tasks has led to superlative claims about their performance. For the evaluation of machine translation (MT), existing research shows that LLMs are able to achieve results
Externí odkaz:
http://arxiv.org/abs/2410.03278
Autor:
Rexhepi, Getuar, Ranasinghe, Kuranage Roche Rayan, de Abreu, Giuseppe Thadeu Freitas, G, David González
We consider the peak-to-average power ratio (PAPR) reduction challenge of orthogonal frequency division multiplexing (OFDM) systems utilizing tone reservation (TR) under a sensing-enabling constraint, such that the signals placed in the reserved tone
Externí odkaz:
http://arxiv.org/abs/2409.16121
Neural networks are powerful function approximators, yet their ``black-box" nature often renders them opaque and difficult to interpret. While many post-hoc explanation methods exist, they typically fail to capture the underlying reasoning processes
Externí odkaz:
http://arxiv.org/abs/2408.14780
Autor:
Doan, Bao Gia, Nguyen, Dang Quang, Lindquist, Callum, Montague, Paul, Abraham, Tamas, De Vel, Olivier, Camtepe, Seyit, Kanhere, Salil S., Abbasnejad, Ehsan, Ranasinghe, Damith C.
Object detectors are vulnerable to backdoor attacks. In contrast to classifiers, detectors possess unique characteristics, architecturally and in task execution; often operating in challenging conditions, for instance, detecting traffic signs in auto
Externí odkaz:
http://arxiv.org/abs/2408.12122
Autor:
Pandita, Deepak, Weerasooriya, Tharindu Cyril, Dutta, Sujan, Luger, Sarah K., Ranasinghe, Tharindu, KhudaBukhsh, Ashiqur R., Zampieri, Marcos, Homan, Christopher M.
Human feedback is essential for building human-centered AI systems across domains where disagreement is prevalent, such as AI safety, content moderation, or sentiment analysis. Many disagreements, particularly in politically charged settings, arise b
Externí odkaz:
http://arxiv.org/abs/2408.08411
Autor:
Doan, Bao Gia, Shamsi, Afshar, Guo, Xiao-Yu, Mohammadi, Arash, Alinejad-Rokny, Hamid, Sejdinovic, Dino, Ranasinghe, Damith C., Abbasnejad, Ehsan
Computational complexity of Bayesian learning is impeding its adoption in practical, large-scale tasks. Despite demonstrations of significant merits such as improved robustness and resilience to unseen or out-of-distribution inputs over their non- Ba
Externí odkaz:
http://arxiv.org/abs/2407.20891