Zobrazeno 1 - 10
of 7 736
pro vyhledávání: '"WEI GU"'
Autor:
Lee, Benjamin C., Brooks, David, van Benthem, Arthur, Gupta, Udit, Hills, Gage, Liu, Vincent, Pierce, Benjamin, Stewart, Christopher, Strubell, Emma, Wei, Gu-Yeon, Wierman, Adam, Yao, Yuan, Yu, Minlan
Computing is at a moment of profound opportunity. Emerging applications -- such as capable artificial intelligence, immersive virtual realities, and pervasive sensor systems -- drive unprecedented demand for computer. Despite recent advances toward n
Externí odkaz:
http://arxiv.org/abs/2405.13858
Autor:
Golden, Alicia, Hsia, Samuel, Sun, Fei, Acun, Bilge, Hosmer, Basil, Lee, Yejin, DeVito, Zachary, Johnson, Jeff, Wei, Gu-Yeon, Brooks, David, Wu, Carole-Jean
Training large-scale machine learning models poses distinct system challenges, given both the size and complexity of today's workloads. Recently, many organizations training state-of-the-art Generative AI models have reported cases of instability dur
Externí odkaz:
http://arxiv.org/abs/2405.02803
Autor:
Brumar, Iulian, Rocha, Rodrigo, Bernat, Alex, Tripathy, Devashree, Brooks, David, Wei, Gu-Yeon
Designing accelerators for resource- and power-constrained applications is a daunting task. High-level Synthesis (HLS) addresses these constraints through resource sharing, an optimization at the HLS binding stage that maps multiple operations to the
Externí odkaz:
http://arxiv.org/abs/2402.13513
This paper presents Flash, an optimized private inference (PI) hybrid protocol utilizing both homomorphic encryption (HE) and secure two-party computation (2PC), which can reduce the end-to-end PI latency for deep CNN models less than 1 minute with C
Externí odkaz:
http://arxiv.org/abs/2401.16732
Autor:
Golden, Alicia, Hsia, Samuel, Sun, Fei, Acun, Bilge, Hosmer, Basil, Lee, Yejin, DeVito, Zachary, Johnson, Jeff, Wei, Gu-Yeon, Brooks, David, Wu, Carole-Jean
As the development of large-scale Generative AI models evolve beyond text (1D) generation to include image (2D) and video (3D) generation, processing spatial and temporal information presents unique challenges to quality, performance, and efficiency.
Externí odkaz:
http://arxiv.org/abs/2312.14385
Autor:
Wasim, Syed Talal, Soboka, Kabila Haile, Mahmoud, Abdulrahman, Khan, Salman, Brooks, David, Wei, Gu-Yeon
This paper presents a novel method to enhance the reliability of image classification models during deployment in the face of transient hardware errors. By utilizing enriched text embeddings derived from GPT-3 with question prompts per class and CLIP
Externí odkaz:
http://arxiv.org/abs/2311.14062
Autor:
Hsia, Samuel, Golden, Alicia, Acun, Bilge, Ardalani, Newsha, DeVito, Zachary, Wei, Gu-Yeon, Brooks, David, Wu, Carole-Jean
Training and deploying large-scale machine learning models is time-consuming, requires significant distributed computing infrastructures, and incurs high operational costs. Our analysis, grounded in real-world large model training on datacenter-scale
Externí odkaz:
http://arxiv.org/abs/2310.02784
Publikováno v:
Communications Biology, Vol 7, Iss 1, Pp 1-12 (2024)
Abstract As a newly defined type of programmed cell death, ferroptosis is considered a potent weapon against tumors due to its distinct mechanism from other types of programmed cell death. Ferroptosis is triggered by the uncontrolled accumulation of
Externí odkaz:
https://doaj.org/article/4a6e6d6044c244a194367e40baf8a982
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-11 (2024)
Abstract Four-membered carbocycles are among the most sought-after backbones which are commonly found in biologically active molecules. However, difficulties on their producing are existing due to its highly strained ring system. On the other hand, c
Externí odkaz:
https://doaj.org/article/71f5762e1587424ba50b9e35dbfa597d
Publikováno v:
IET Generation, Transmission & Distribution, Vol 18, Iss 19, Pp 3108-3119 (2024)
Abstract This article proposes a unilateral Adaptive update strategy based Interval Prediction (AIP) model for short‐term load prediction, which is developed based on lower and upper bound estimation (LUBE) architecture. In traditional LUBE interva
Externí odkaz:
https://doaj.org/article/b21e93dbf4c5465fbd4d1f113f610d30