Zobrazeno 1 - 10
of 5 319
pro vyhledávání: '"Venkataramani AS"'
Synthetic data is becoming increasingly integral in data-scarce fields such as medical imaging, serving as a substitute for real data. However, its inherent statistical characteristics can significantly impact downstream tasks, potentially compromisi
Externí odkaz:
http://arxiv.org/abs/2407.21674
Autor:
Xie, Rui, Haq, Asad Ul, Ma, Linsen, Sun, Krystal, Sen, Sanchari, Venkataramani, Swagath, Liu, Liu, Zhang, Tong
Recent studies have revealed that, during the inference on generative AI models such as transformer, the importance of different weights exhibits substantial context-dependent variations. This naturally manifests a promising potential of adaptively c
Externí odkaz:
http://arxiv.org/abs/2407.15866
Autor:
Gogineni, Kailash, Dayapule, Sai Santosh, Gómez-Luna, Juan, Gogineni, Karthikeya, Wei, Peng, Lan, Tian, Sadrosadati, Mohammad, Mutlu, Onur, Venkataramani, Guru
Reinforcement Learning (RL) trains agents to learn optimal behavior by maximizing reward signals from experience datasets. However, RL training often faces memory limitations, leading to execution latencies and prolonged training times. To overcome t
Externí odkaz:
http://arxiv.org/abs/2405.03967
Autor:
Aravind, K, Venkataramani, Kumar, Ganesh, Shashikiran, Surya, Arun, Sivarani, Thirupathi, Sahu, Devendra, Unni, Athira, Bhardwaj, Anil
Observing the vibrational/rotational lines in a comet's optical spectrum requires high-resolution spectroscopy, as they are otherwise seen as a blended feature. To achieve this, we have obtained medium and high-resolution (R ($\lambda/\Delta \lambda$
Externí odkaz:
http://arxiv.org/abs/2403.01595
Deep Neural Networks (DNNs) have revolutionized a wide range of industries, from healthcare and finance to automotive, by offering unparalleled capabilities in data analysis and decision-making. Despite their transforming impact, DNNs face two critic
Externí odkaz:
http://arxiv.org/abs/2402.04325
Jupiter Family Comets (JFCs), having orbital period less than 20 years, provide us with an opportunity to observe their activity and analyse the homogeneity in their coma composition over multiple apparitions. Comet 46P/Wirtanen with its exceptionall
Externí odkaz:
http://arxiv.org/abs/2401.03869
Promptable foundation models, particularly Segment Anything Model (SAM), have emerged as a promising alternative to the traditional task-specific supervised learning for image segmentation. However, many evaluation studies have found that their perfo
Externí odkaz:
http://arxiv.org/abs/2310.17128
Cross-device Federated Learning (FL) faces significant challenges where low-end clients that could potentially make unique contributions are excluded from training large models due to their resource bottlenecks. Recent research efforts have focused o
Externí odkaz:
http://arxiv.org/abs/2310.08670
We develop a discrete differential geometry for surfaces of non-constant negative curvature, which can be used to model various phenomena from the growth of flower petals to marine invertebrate swimming. Specifically, we derive and numerically integr
Externí odkaz:
http://arxiv.org/abs/2309.08117
Autor:
Banerjee, Krishnarjun, Pandey, Adityanarayan H., Varade, Pravin, Kulkarni, Ajit R., Sangle, Abhijeet L., Venkataramani, N.
Pb-free ferroelectric thin films are gaining attention due to their applicability in memory, sensor, actuator, and microelectromechanical system. In this work, Na$_{0.4}$K$_{0.1}$Bi$_{0.5}$TiO$_3$ (NKBT0.1) ferroelectric thin films were deposited on
Externí odkaz:
http://arxiv.org/abs/2308.03124