Zobrazeno 1 - 10
of 209
pro vyhledávání: '"Liu, Jiangjiang"'
Multimodal RLHF usually happens after supervised finetuning (SFT) stage to continually improve vision-language models' (VLMs) comprehension. Conventional wisdom holds its superiority over continual SFT during this preference alignment stage. In this
Externí odkaz:
http://arxiv.org/abs/2411.14797
Autor:
Li, Jiankun, Li, Hao, Liu, Jiangjiang, Zou, Zhikang, Ye, Xiaoqing, Wang, Fan, Huang, Jizhou, Wu, Hua, Wang, Haifeng
Deep learning-based models are widely deployed in autonomous driving areas, especially the increasingly noticed end-to-end solutions. However, the black-box property of these models raises concerns about their trustworthiness and safety for autonomou
Externí odkaz:
http://arxiv.org/abs/2407.06546
Autor:
Long, Sifan, Zhao, Zhen, Yuan, Junkun, Tan, Zichang, Liu, Jiangjiang, Zhou, Luping, Wang, Shengsheng, Wang, Jingdong
Prompt learning has become one of the most efficient paradigms for adapting large pre-trained vision-language models to downstream tasks. Current state-of-the-art methods, like CoOp and ProDA, tend to adopt soft prompts to learn an appropriate prompt
Externí odkaz:
http://arxiv.org/abs/2303.17169
Autor:
Cui, Yiping, Xiao, Xin, Wang, Mumu, Zhu, Mengjiao, Yuyama, Nana, Zheng, Jingru, Xiong, Candong, Liu, Jiangjiang, Wang, Sumeng, Yang, Yuru, Chen, Jun, Cai, Hongwei
Publikováno v:
In Plant Science November 2024 348
Autor:
Liu, Jiangjiang, Tian, Bian, Lu, Nengchao, Liu, Zhaojun, Zhang, Zhongkai, Shi, Meng, Fang, Xudong, Feng, Ke, Tan, Qing, Liu, Dan, Shi, Peng, Zhao, Libo, Ren, Wei, Jiang, Zhuangde
Publikováno v:
In Ceramics International 1 December 2024 50(23) Part C:52027-52035
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Fully convolutional neural networks (FCNs) have shown their advantages in the salient object detection task. However, most existing FCNs-based methods still suffer from coarse object boundaries. In this paper, to solve this problem, we focus on the c
Externí odkaz:
http://arxiv.org/abs/1908.08297
Autor:
Liu, Zhaojun, Tian, Bian, Liu, Xiang, Zhang, Xuefeng, Li, Yao, Zhang, Zhongkai, Liu, Jiangjiang, Lin, Qijing, Jiang, Zhuangde
Publikováno v:
In Journal of Alloys and Compounds 25 April 2023 941
Autor:
Wu, Zunchun, Li, Ruhong, Zhang, Shuoqing, lv, Ling, Deng, Tao, Zhang, Hao, Zhang, Ruixin, Liu, Jiangjiang, Ding, Shouhong, Fan, Liwu, Chen, Lixin, Fan, Xiulin
Publikováno v:
In Chem 9 March 2023 9(3):650-664