Zobrazeno 1 - 10
of 116
pro vyhledávání: '"Wang Zifu"'
Autor:
Ning, Xuefei, Wang, Zifu, Li, Shiyao, Lin, Zinan, Yao, Peiran, Fu, Tianyu, Blaschko, Matthew B., Dai, Guohao, Yang, Huazhong, Wang, Yu
Teaching to improve student models (e.g., knowledge distillation) is an extensively studied methodology in LLMs. However, for humans, teaching not only improves students but also improves teachers. We ask: Can LLMs also learn by teaching (LbT)? If ye
Externí odkaz:
http://arxiv.org/abs/2406.14629
Autor:
Wang, Zifu, Berman, Maxim, Rannen-Triki, Amal, Torr, Philip H. S., Tuia, Devis, Tuytelaars, Tinne, Van Gool, Luc, Yu, Jiaqian, Blaschko, Matthew B.
Semantic segmentation datasets often exhibit two types of imbalance: \textit{class imbalance}, where some classes appear more frequently than others and \textit{size imbalance}, where some objects occupy more pixels than others. This causes tradition
Externí odkaz:
http://arxiv.org/abs/2310.19252
This work aims at decreasing the end-to-end generation latency of large language models (LLMs). One of the major causes of the high generation latency is the sequential decoding approach adopted by almost all state-of-the-art LLMs. In this work, moti
Externí odkaz:
http://arxiv.org/abs/2307.15337
The soft Dice loss (SDL) has taken a pivotal role in numerous automated segmentation pipelines in the medical imaging community. Over the last years, some reasons behind its superior functioning have been uncovered and further optimizations have been
Externí odkaz:
http://arxiv.org/abs/2303.16296
Intersection over Union (IoU) losses are surrogates that directly optimize the Jaccard index. Leveraging IoU losses as part of the loss function have demonstrated superior performance in semantic segmentation tasks compared to optimizing pixel-wise l
Externí odkaz:
http://arxiv.org/abs/2302.05666
Autor:
Zhao, Peng1 (AUTHOR) aligaduo103849724@163.com, Wang, Zifu1 (AUTHOR) wang_zi_fu@163.com, Liao, Shimei1 (AUTHOR) liao5253leg@163.com, Liao, Yangxin1 (AUTHOR) lyx258xxxxx@163.com, Hu, Shijun2 (AUTHOR) shijunhu@swfu.edu.cn, Qin, Jianchun3 (AUTHOR) qinjc@jlu.edu.cn, Zhang, Donghua1 (AUTHOR) fooifoot@swfu.edu.cn, Yan, Xiaohui1 (AUTHOR) fooifoot@swfu.edu.cn
Publikováno v:
International Journal of Molecular Sciences. Sep2024, Vol. 25 Issue 18, p10188. 15p.
Autor:
Wang, Zifu, Luo, Liyang, Xia, Di, Lu, Siqi, Lin, Guosheng, Gao, Shecheng, Zhang, Bin, Li, Zhaohui
Broadband Kerr combs with a flat comb spectral profile are expected in a number of applications, such as high-capacity optical communication. Here, we propose novel concentric dual-ring microresonators (DRMs) for advanced dispersion engineering to ta
Externí odkaz:
http://arxiv.org/abs/2210.09543
Autor:
Wang, Zifu, Blaschko, Matthew B.
UNet [27] is widely used in semantic segmentation due to its simplicity and effectiveness. However, its manually-designed architecture is applied to a large number of problem settings, either with no architecture optimizations, or with manual tuning,
Externí odkaz:
http://arxiv.org/abs/2207.06168
Autor:
Xia, Di, Yang, Zelin, Zeng, Pingyang, Zhang, Bin, Wu, Jiayue, Wang, Zifu, Zhao, Jiaxin, Gao, Mingqi, Huang, Yufei, Huang, Jianteng, Luo, Liyang, Liu, Dong, Yang, Shuixian, Guo, Hairun, Li, Zhaohui
Publikováno v:
Laser & Photonics Reviews 16 202200219 (2022)
Photonic integrated microcombs have enabled advanced applications in optical communication, microwave synthesis, and optical metrology, which in nature unveil an optical dissipative soliton pattern under cavity-enhanced nonlinear processes. The most
Externí odkaz:
http://arxiv.org/abs/2202.05992
Autor:
Zhang, Bo, Li, Xiaoran, Wang, Zifu, Ren, Huimin, Wang, Jianhui, Chen, Qijie, Cai, Yongjian, Quan, Ke, Liu, Miao, Pan, Mingfei, Fang, Guozhen
Publikováno v:
In Talanta 1 September 2024 277