Zobrazeno 1 - 10
of 8 534
pro vyhledávání: '"P. Shafi"'
Machine learning models for graphs in real-world applications are prone to two primary types of uncertainty: (1) those that arise from incomplete and noisy data and (2) those that arise from uncertainty of the model in its output. These sources of un
Externí odkaz:
http://arxiv.org/abs/2412.05735
Mobile communications have been undergoing a generational change every ten years. While 5G network deployments are maturing, significant efforts are being made to standardize 6G, which is expected to be commercially introduced by 2030. This paper pro
Externí odkaz:
http://arxiv.org/abs/2411.18836
As society grows more reliant on machine learning, ensuring the security of machine learning systems against sophisticated attacks becomes a pressing concern. A recent result of Goldwasser, Kim, Vaikuntanathan, and Zamir (2022) shows that an adversar
Externí odkaz:
http://arxiv.org/abs/2411.03279
The widespread dissemination of false information through manipulative tactics that combine deceptive text and images threatens the integrity of reliable sources of information. While there has been research on detecting fake news in high resource la
Externí odkaz:
http://arxiv.org/abs/2410.10407
Autor:
Dar, Shahid Shafi, Rehman, Mohammad Zia Ur, Bais, Karan, Haseeb, Mohammed Abdul, Kumara, Nagendra
Publikováno v:
journal={Expert Systems with Applications},pages={125337},year={2024},publisher={Elsevier}
In times of crisis, the prompt and precise classification of disaster-related information shared on social media platforms is crucial for effective disaster response and public safety. During such critical events, individuals use social media to comm
Externí odkaz:
http://arxiv.org/abs/2410.08814
We explore the cosmological and astrophysical implications of a realistic hybrid inflation model based on flipped $SU(5)$. The model contains superheavy metastable cosmic strings arising from a waterfall field that encounters a limited number of $e$-
Externí odkaz:
http://arxiv.org/abs/2409.13584
Autor:
Xu, Lang, Anthony, Quentin, Zhou, Qinghua, Alnaasan, Nawras, Gulhane, Radha R., Shafi, Aamir, Subramoni, Hari, Panda, Dhabaleswar K.
Data Parallelism (DP), Tensor Parallelism (TP), and Pipeline Parallelism (PP) are the three strategies widely adopted to enable fast and efficient Large Language Model (LLM) training. However, these approaches rely on data-intensive communication rou
Externí odkaz:
http://arxiv.org/abs/2409.02423
Autor:
Yao, Jinghan, Jacobs, Sam Ade, Tanaka, Masahiro, Ruwase, Olatunji, Shafi, Aamir, Subramoni, Hari, Panda, Dhabaleswar K.
Large Language Models (LLMs) with long context capabilities are integral to complex tasks in natural language processing and computational biology, such as text generation and protein sequence analysis. However, training LLMs directly on extremely lo
Externí odkaz:
http://arxiv.org/abs/2408.16978
Autor:
Maji, Rinku, Shafi, Qaisar
Publikováno v:
JHEP 10 (2024) 157
We present an $SO(10)$ model in which a dimension five operator induces kinetic mixing at the GUT scale between the abelian subgroups $U(1)_{B-L}$ and $U(1)_R$. We discuss in this framework gauge coupling unification and proton decay, as well as the
Externí odkaz:
http://arxiv.org/abs/2408.14350
Autor:
Hadiuzzaman, Md, Ali, Mohammed Sowket, Sultana, Tamanna, Shafi, Abdur Raj, Miah, Abu Saleh Musa, Shin, Jungpil
People commonly communicate in English, Arabic, and Bengali spoken languages through various mediums. However, deaf and hard-of-hearing individuals primarily use body language and sign language to express their needs and achieve independence. Sign la
Externí odkaz:
http://arxiv.org/abs/2408.10518