Zobrazeno 1 - 10
of 230
pro vyhledávání: '"Lu, Yung Hsiang"'
Autor:
Hasler, Ryan, Läufer, Konstantin, Thiruvathukal, George K., Peng, Huiyun, Robinson, Kyle, Davis, Kirsten, Lu, Yung-Hsiang, Davis, James C.
Computing systems are consuming an increasing and unsustainable fraction of society's energy footprint, notably in data centers. Meanwhile, energy-efficient software engineering techniques are often absent from undergraduate curricula. We propose to
Externí odkaz:
http://arxiv.org/abs/2411.08912
Autor:
Peng, Huiyun, Gupte, Arjun, Eliopoulos, Nicholas John, Ho, Chien Chou, Mantri, Rishi, Deng, Leo, Jiang, Wenxin, Lu, Yung-Hsiang, Läufer, Konstantin, Thiruvathukal, George K., Davis, James C.
Energy-efficient software helps improve mobile device experiences and reduce the carbon footprint of data centers. However, energy goals are often de-prioritized in order to meet other requirements. We take inspiration from recent work exploring the
Externí odkaz:
http://arxiv.org/abs/2410.09241
Autor:
Jajal, Purvish, Eliopoulos, Nick John, Chou, Benjamin Shiue-Hal, Thiravathukal, George K., Davis, James C., Lu, Yung-Hsiang
We propose Vision Token Turing Machines (ViTTM), an efficient, low-latency, memory-augmented Vision Transformer (ViT). Our approach builds on Neural Turing Machines and Token Turing Machines, which were applied to NLP and sequential visual understand
Externí odkaz:
http://arxiv.org/abs/2409.07613
Autor:
Eliopoulos, Nick John, Jajal, Purvish, Davis, James C., Liu, Gaowen, Thiravathukal, George K., Lu, Yung-Hsiang
This paper investigates how to efficiently deploy vision transformers on edge devices for small workloads. Recent methods reduce the latency of transformer neural networks by removing or merging tokens, with small accuracy degradation. However, these
Externí odkaz:
http://arxiv.org/abs/2407.05941
Autor:
Chen, Leo, Boardley, Benjamin, Hu, Ping, Wang, Yiru, Pu, Yifan, Jin, Xin, Yao, Yongqiang, Gong, Ruihao, Li, Bo, Huang, Gao, Liu, Xianglong, Wan, Zifu, Chen, Xinwang, Liu, Ning, Zhang, Ziyi, Liu, Dongping, Shan, Ruijie, Che, Zhengping, Zhang, Fachao, Mou, Xiaofeng, Tang, Jian, Chuprov, Maxim, Malofeev, Ivan, Goncharenko, Alexander, Shcherbin, Andrey, Yanchenko, Arseny, Alyamkin, Sergey, Hu, Xiao, Thiruvathukal, George K., Lu, Yung Hsiang
This article describes the 2023 IEEE Low-Power Computer Vision Challenge (LPCVC). Since 2015, LPCVC has been an international competition devoted to tackling the challenge of computer vision (CV) on edge devices. Most CV researchers focus on improvin
Externí odkaz:
http://arxiv.org/abs/2403.07153
Autor:
Tung, Caleb, Eliopoulos, Nicholas, Jajal, Purvish, Ramshankar, Gowri, Yang, Chen-Yun, Synovic, Nicholas, Zhang, Xuecen, Chaudhary, Vipin, Thiruvathukal, George K., Lu, Yung-Hsiang
Computer vision often uses highly accurate Convolutional Neural Networks (CNNs), but these deep learning models are associated with ever-increasing energy and computation requirements. Producing more energy-efficient CNNs often requires model trainin
Externí odkaz:
http://arxiv.org/abs/2310.07782
Analysis of Failures and Risks in Deep Learning Model Converters: A Case Study in the ONNX Ecosystem
Autor:
Jajal, Purvish, Jiang, Wenxin, Tewari, Arav, Kocinare, Erik, Woo, Joseph, Sarraf, Anusha, Lu, Yung-Hsiang, Thiruvathukal, George K., Davis, James C.
Software engineers develop, fine-tune, and deploy deep learning (DL) models using a variety of development frameworks and runtime environments. DL model converters move models between frameworks and to runtime environments. Conversion errors compromi
Externí odkaz:
http://arxiv.org/abs/2303.17708
Autor:
Jiang, Wenxin, Synovic, Nicholas, Hyatt, Matt, Schorlemmer, Taylor R., Sethi, Rohan, Lu, Yung-Hsiang, Thiruvathukal, George K., Davis, James C.
Deep Neural Networks (DNNs) are being adopted as components in software systems. Creating and specializing DNNs from scratch has grown increasingly difficult as state-of-the-art architectures grow more complex. Following the path of traditional softw
Externí odkaz:
http://arxiv.org/abs/2303.02552
Autor:
Tung, Caleb, Goel, Abhinav, Bordwell, Fischer, Eliopoulos, Nick, Hu, Xiao, Thiruvathukal, George K., Lu, Yung-Hsiang
Object detectors are vital to many modern computer vision applications. However, even state-of-the-art object detectors are not perfect. On two images that look similar to human eyes, the same detector can make different predictions because of small
Externí odkaz:
http://arxiv.org/abs/2207.13890