Zobrazeno 1 - 10
of 263
pro vyhledávání: '"Wu, Pei‐Yuan"'
The reasoning abilities of large language models (LLMs) have improved with chain-of-thought (CoT) prompting, allowing models to solve complex tasks in a stepwise manner. However, training CoT capabilities requires detailed reasoning data, which is of
Externí odkaz:
http://arxiv.org/abs/2410.23912
Offline reinforcement learning (RL) learns policies from a fixed dataset, but often requires large amounts of data. The challenge arises when labeled datasets are expensive, especially when rewards have to be provided by human labelers for large data
Externí odkaz:
http://arxiv.org/abs/2408.12307
This study uses CAPM (Convex Adversarial Polytope for Maxpool-based CNN) to improve the verified bound for general purpose maxpool-based convolutional neural networks (CNNs) under bounded norm adversarial perturbations. The maxpool function is decomp
Externí odkaz:
http://arxiv.org/abs/2407.09550
Autor:
Yeh, Sing-Yuan, Chang, Fu-Chieh, Yueh, Chang-Wei, Wu, Pei-Yuan, Bernacchia, Alberto, Vakili, Sattar
Modern reinforcement learning (RL) often faces an enormous state-action space. Existing analytical results are typically for settings with a small number of state-actions, or simple models such as linearly modeled Q-functions. To derive statistically
Externí odkaz:
http://arxiv.org/abs/2302.00727
Autor:
Ancuti, Codruta O., Ancuti, Cosmin, Vasluianu, Florin-Alexandru, Timofte, Radu, Liu, Jing, Wu, Haiyan, Xie, Yuan, Qu, Yanyun, Ma, Lizhuang, Huang, Ziling, Deng, Qili, Chao, Ju-Chin, Yang, Tsung-Shan, Chen, Peng-Wen, Hsu, Po-Min, Liao, Tzu-Yi, Sun, Chung-En, Wu, Pei-Yuan, Do, Jeonghyeok, Park, Jongmin, Kim, Munchurl, Metwaly, Kareem, Li, Xuelu, Guo, Tiantong, Monga, Vishal, Yu, Mingzhao, Cherukuri, Venkateswararao, Chuang, Shiue-Yuan, Lin, Tsung-Nan, Lee, David, Chang, Jerome, Wang, Zhan-Han, Chang, Yu-Bang, Lin, Chang-Hong, Dong, Yu, Zhou, Hongyu, Kong, Xiangzhen, Das, Sourya Dipta, Dutta, Saikat, Zhao, Xuan, Ouyang, Bing, Estrada, Dennis, Wang, Meiqi, Su, Tianqi, Chen, Siyi, Sun, Bangyong, de Dravo, Vincent Whannou, Yu, Zhe, Narang, Pratik, Mehra, Aryan, Raghunath, Navaneeth, Mandal, Murari
This paper reviews the NTIRE 2020 Challenge on NonHomogeneous Dehazing of images (restoration of rich details in hazy image). We focus on the proposed solutions and their results evaluated on NH-Haze, a novel dataset consisting of 55 pairs of real ha
Externí odkaz:
http://arxiv.org/abs/2005.03457
Publikováno v:
In Journal of Mathematical Analysis and Applications 1 December 2023 528(1)
Autor:
Qiu, Yong-Qiang *, Zhuang, Lv-Ping, Wu, Pei-Yuan, Zhong, Li-Ying, Zhong, Xiao-Hui, Chen, Bin, Liu, Zhong-Kai, Luo, Hui-Rong **, Yang, Li-Ping
Publikováno v:
In Journal of Cardiothoracic and Vascular Anesthesia August 2023 37(8):1424-1432
Publikováno v:
Published in Neurocomputing 2020
Protecting sensitive information against data exploiting attacks is an emerging research area in data mining. Over the past, several different methods have been introduced to protect individual privacy from such attacks while maximizing data-utility
Externí odkaz:
http://arxiv.org/abs/1902.10799
Autor:
Wu, Pei-Yuan, 吳培源
105
Experienced dynamic growth for decades, enterprises in Taiwan are now facing stagnation due to challenges to their original advantage of competitiveness such as cost saving strategy of utilizing low cost labor, well-developed industrial clus
Experienced dynamic growth for decades, enterprises in Taiwan are now facing stagnation due to challenges to their original advantage of competitiveness such as cost saving strategy of utilizing low cost labor, well-developed industrial clus
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/9j852e