Zobrazeno 1 - 10
of 54 546
pro vyhledávání: '"Indra ."'
The success of deep learning in supervised fine-grained recognition for domain-specific tasks relies heavily on expert annotations. The Open-Set for fine-grained Self-Supervised Learning (SSL) problem aims to enhance performance on downstream tasks b
Externí odkaz:
http://arxiv.org/abs/2412.16942
We study in detail the production of primordial black holes (PBHs), as well as their mass and initial spin, due to the phase transitions corresponding to radiative symmetry breaking (RSB) and featuring a large supercooling. The latter property allows
Externí odkaz:
http://arxiv.org/abs/2412.06889
Autor:
Alam, Nahid, Kanjula, Karthik Reddy, Guthikonda, Surya, Chung, Timothy, Vegesna, Bala Krishna S, Das, Abhipsha, Susevski, Anthony, Chan, Ryan Sze-Yin, Uddin, S M Iftekhar, Islam, Shayekh Bin, Santhosh, Roshan, A, Snegha, Sharma, Drishti, Liu, Chen, Chaturvedi, Isha, Winata, Genta Indra, S, Ashvanth., Mukherjee, Snehanshu, Aji, Alham Fikri
The rapid development of large Vision-Language Models (VLMs) has led to impressive results on academic benchmarks, primarily in widely spoken languages. However, significant gaps remain in the ability of current VLMs to handle low-resource languages
Externí odkaz:
http://arxiv.org/abs/2412.07112
Autor:
Dutta, Kunal, Dasgupta, Indra
In this paper, we have proposed a novel route for the realisation of persistent spin texture (PST). We have shown from symmetry considerations that in non-polar chiral systems, bands with specific orbital characters around a high symmetry point with
Externí odkaz:
http://arxiv.org/abs/2412.03229
Background: Explainability in phishing detection model can support a further solution of phishing attack mitigation by increasing trust and understanding how phishing can be detected. Objective: The aims of this study to determine and best recommenda
Externí odkaz:
http://arxiv.org/abs/2412.02084
Autor:
Kampman, Onno P., Phang, Ye Sheng, Han, Stanley, Xing, Michael, Hong, Xinyi, Hoosainsah, Hazirah, Tan, Caleb, Winata, Genta Indra, Wang, Skyler, Heaukulani, Creighton, Weng, Janice Huiqin, Morris, Robert JT
We introduce a general-purpose, human-in-the-loop dual dialogue system to support mental health care professionals. The system, co-designed with care providers, is conceptualized to assist them in interacting with care seekers rather than functioning
Externí odkaz:
http://arxiv.org/abs/2411.18429
Phishing attacks remain a persistent threat to online security, demanding robust detection methods. This study investigates the use of machine learning to identify phishing URLs, emphasizing the crucial role of feature selection and model interpretab
Externí odkaz:
http://arxiv.org/abs/2411.06860
We present MetaMetrics-MT, an innovative metric designed to evaluate machine translation (MT) tasks by aligning closely with human preferences through Bayesian optimization with Gaussian Processes. MetaMetrics-MT enhances existing MT metrics by optim
Externí odkaz:
http://arxiv.org/abs/2411.00390