Výsledky vyhledávání - "Wang Fengxiang"

Report

MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue

Autor: Wang, Fengxiang, Duan, Ranjie, Xiao, Peng, Jia, Xiaojun, Chen, YueFeng, Wang, Chongwen, Tao, Jialing, Su, Hang, Zhu, Jun, Xue, Hui

Large Language Models (LLMs) demonstrate outstanding performance in their reservoir of knowledge and understanding capabilities, but they have also been shown to be prone to illegal or unethical reactions when subjected to jailbreak attacks. To ensur

Externí odkaz: http://arxiv.org/abs/2411.03814

Zobrazit plný text záznamu

Report

Scaling Efficient Masked Image Modeling on Large Remote Sensing Dataset

Autor: Wang, Fengxiang, Wang, Hongzhen, Wang, Di, Guo, Zonghao, Zhong, Zhenyu, Lan, Long, Zhang, Jing, Liu, Zhiyuan, Sun, Maosong

Masked Image Modeling (MIM) has become an essential method for building foundational visual models in remote sensing (RS). However, the limitations in size and diversity of existing RS datasets restrict the ability of MIM methods to learn generalizab

Externí odkaz: http://arxiv.org/abs/2406.11933

Zobrazit plný text záznamu

Report

Efficient Prompt Tuning of Large Vision-Language Model for Fine-Grained Ship Classification

Autor: Lan, Long, Wang, Fengxiang, Zheng, Xiangtao, Wang, Zengmao, Liu, Xinwang

Fine-grained ship classification in remote sensing (RS-FGSC) poses a significant challenge due to the high similarity between classes and the limited availability of labeled data, limiting the effectiveness of traditional supervised classification me

Externí odkaz: http://arxiv.org/abs/2403.08271

Zobrazit plný text záznamu