Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Zhu, Xunyu"'
Large Language Models (LLMs) have demonstrated exceptional proficiency in mathematical reasoning tasks due to their extensive parameter counts and training on vast datasets. Despite these capabilities, deploying LLMs is hindered by their computationa
Externí odkaz:
http://arxiv.org/abs/2407.10167
This work addresses the challenge of democratizing advanced Large Language Models (LLMs) by compressing their mathematical reasoning capabilities into sub-billion parameter Small Language Models (SLMs) without compromising performance. We introduce E
Externí odkaz:
http://arxiv.org/abs/2401.11864
Large Language Models (LLMs) have transformed natural language processing tasks successfully. Yet, their large size and high computational needs pose challenges for practical use, especially in resource-limited settings. Model compression has emerged
Externí odkaz:
http://arxiv.org/abs/2308.07633
Neural Architectures Search (NAS) becomes more and more popular over these years. However, NAS-generated models tends to suffer greater vulnerability to various malicious attacks. Lots of robust NAS methods leverage adversarial training to enhance th
Externí odkaz:
http://arxiv.org/abs/2304.02845
Differentiable Neural Architecture Search (DARTS) is becoming more and more popular among Neural Architecture Search (NAS) methods because of its high search efficiency and low compute cost. However, the stability of DARTS is very inferior, especiall
Externí odkaz:
http://arxiv.org/abs/2302.05632
Differentiable Architecture Search (DARTS) is a simple yet efficient Neural Architecture Search (NAS) method. During the search stage, DARTS trains a supernet by jointly optimizing architecture parameters and network parameters. During the evaluation
Externí odkaz:
http://arxiv.org/abs/2302.05629
Autor:
Zhu, Xunyu
Thesis (Ph. D.)--Oklahoma State University, 2005.
Vita. Includes bibliographical references (p.113-116).
Vita. Includes bibliographical references (p.113-116).
Externí odkaz:
http://digital.library.okstate.edu/etd/umi-okstate-1460.pdf
Publikováno v:
Region 5 Conference, 2006 IEEE; 2006, p83-86, 4p
Autor:
Zhu X; Institute of Information Engineering, Chinese Academy of Sciences, China; School of Cyber Security, University of Chinese Academy of Sciences, China. Electronic address: zhuxunyu@iie.ac.cn., Li J; Institute of Information Engineering, Chinese Academy of Sciences, China; School of Cyber Security, University of Chinese Academy of Sciences, China. Electronic address: lijian9026@iie.ac.cn., Liu Y; Gaoling School of Artificial Intelligence, Renmin University of China, China. Electronic address: liuyonggsai@ruc.edu.cn., Ma C; Institute of Information Engineering, Chinese Academy of Sciences, China; School of Cyber Security, University of Chinese Academy of Sciences, China. Electronic address: macan@iie.ac.cn., Wang W; Institute of Information Engineering, Chinese Academy of Sciences, China; School of Cyber Security, University of Chinese Academy of Sciences, China. Electronic address: wangweiping@iie.ac.cn.
Publikováno v:
Neural networks : the official journal of the International Neural Network Society [Neural Netw] 2024 Nov; Vol. 179, pp. 106594. Date of Electronic Publication: 2024 Aug 02.
Autor:
Zhu X; Institute of Information Engineering, Chinese Academy of Sciences, China; School of Cyber Security, University of Chinese Academy of Sciences, China. Electronic address: zhuxunyu@iie.ac.cn., Li J; Institute of Information Engineering, Chinese Academy of Sciences, China; School of Cyber Security, University of Chinese Academy of Sciences, China. Electronic address: lijian9026@iie.ac.cn., Liu Y; Gaoling School of Artificial Intelligence, Renmin University of China, China. Electronic address: liuyonggsai@ruc.edu.cn., Wang W; Institute of Information Engineering, Chinese Academy of Sciences, China; School of Cyber Security, University of Chinese Academy of Sciences, China. Electronic address: wangweiping@iie.ac.cn.
Publikováno v:
Neural networks : the official journal of the International Neural Network Society [Neural Netw] 2023 Oct; Vol. 167, pp. 656-667. Date of Electronic Publication: 2023 Sep 09.