Zobrazeno 1 - 10
of 148
pro vyhledávání: '"Sitaraman, Ramesh"'
Text-to-image generation using diffusion models has gained increasing popularity due to their ability to produce high-quality, realistic images based on text prompts. However, efficiently serving these models is challenging due to their computation-i
Externí odkaz:
http://arxiv.org/abs/2411.15381
Ridesharing has experienced significant global growth over the past decade and is becoming integral to future transportation networks. These services offer alternative mobility options in many urban areas, promoting car-light or car-free lifestyles,
Externí odkaz:
http://arxiv.org/abs/2411.01412
The rapid adoption of machine learning (ML) has underscored the importance of serving ML models with high throughput and resource efficiency. Traditional approaches to managing increasing query demands have predominantly focused on hardware scaling,
Externí odkaz:
http://arxiv.org/abs/2407.03583
In recent years, there has been an increased emphasis on reducing the carbon emissions from electricity consumption. Many organizations have set ambitious targets to reduce the carbon footprint of their operations as a part of their sustainability go
Externí odkaz:
http://arxiv.org/abs/2402.03550
Autor:
Wang, Lingdong, Singh, Simran, Chakareski, Jacob, Hajiesmaili, Mohammad, Sitaraman, Ramesh K.
Accessing high-quality video content can be challenging due to insufficient and unstable network bandwidth. Recent advances in neural enhancement have shown promising results in improving the quality of degraded videos through deep learning. Neural-E
Externí odkaz:
http://arxiv.org/abs/2310.09920
Recent advances in omnidirectional cameras and AR/VR headsets have spurred the adoption of 360-degree videos that are widely believed to be the future of online video streaming. 360-degree videos allow users to wear a head-mounted display (HMD) and e
Externí odkaz:
http://arxiv.org/abs/2309.04023
Untangling Carbon-free Energy Attribution and Carbon Intensity Estimation for Carbon-aware Computing
Many organizations, including governments, utilities, and businesses, have set ambitious targets to reduce carbon emissions for their Environmental, Social, and Governance (ESG) goals. To achieve these targets, these organizations increasingly use po
Externí odkaz:
http://arxiv.org/abs/2308.06680
360-degree video has become increasingly popular in content consumption. However, finding the viewing direction for important content within each frame poses a significant challenge. Existing approaches rely on either viewer input or algorithmic dete
Externí odkaz:
http://arxiv.org/abs/2306.08089
Point cloud upsampling is essential for high-quality augmented reality, virtual reality, and telepresence applications, due to the capture, processing, and communication limitations of existing technologies. Although geometry upsampling to densify a
Externí odkaz:
http://arxiv.org/abs/2209.06112
Autor:
Bashir, Noman, Guo, Tian, Hajiesmaili, Mohammad, Irwin, David, Shenoy, Prashant, Sitaraman, Ramesh, Souza, Abel, Wierman, Adam
Cloud platforms' growing energy demand and carbon emissions are raising concern about their environmental sustainability. The current approach to enabling sustainable clouds focuses on improving energy-efficiency and purchasing carbon offsets. These
Externí odkaz:
http://arxiv.org/abs/2106.08872