Zobrazeno 1 - 10
of 6 477
pro vyhledávání: '"ZHANG Zhiwei"'
The quality of training data significantly impacts the performance of large language models (LLMs). There are increasing studies using LLMs to rate and select data based on several human-crafted metrics (rules). However, these conventional rule-based
Externí odkaz:
http://arxiv.org/abs/2410.04715
Autor:
Xu, Zijun, Jin, Rui, Wu, Ke, Zhao, Yi, Zhang, Zhiwei, Zhao, Jieru, Gao, Fei, Gan, Zhongxue, Ding, Wenchao
In complex missions such as search and rescue,robots must make intelligent decisions in unknown environments, relying on their ability to perceive and understand their surroundings. High-quality and real-time reconstruction enhances situational aware
Externí odkaz:
http://arxiv.org/abs/2409.17624
Multi-robot swarms utilize swarm intelligence to collaborate on tasks and play an increasingly significant role in a variety of practical scenarios. However, due to the complex design, multi-robot swarm systems often have vulnerabilities caused by lo
Externí odkaz:
http://arxiv.org/abs/2409.04736
Autor:
Zhang, Zhiwei
Class imbalance is a critical issue in image classification that significantly affects the performance of deep recognition models. In this work, we first identify a network degeneration dilemma that hinders the model learning by introducing a high li
Externí odkaz:
http://arxiv.org/abs/2408.17197
Graph Neural Networks (GNNs) have achieved promising results in tasks such as node classification and graph classification. However, recent studies reveal that GNNs are vulnerable to backdoor attacks, posing a significant threat to their real-world a
Externí odkaz:
http://arxiv.org/abs/2406.09836
Graph Neural Networks (GNNs) have shown remarkable performance in various tasks. However, recent works reveal that GNNs are vulnerable to backdoor attacks. Generally, backdoor attack poisons the graph by attaching backdoor triggers and the target cla
Externí odkaz:
http://arxiv.org/abs/2405.10757
Autor:
Tan, Xin, Wu, Wenbin, Zhang, Zhiwei, Fan, Chaojie, Peng, Yong, Zhang, Zhizhong, Xie, Yuan, Ma, Lizhuang
3D occupancy perception holds a pivotal role in recent vision-centric autonomous driving systems by converting surround-view images into integrated geometric and semantic representations within dense 3D grids. Nevertheless, current models still encou
Externí odkaz:
http://arxiv.org/abs/2405.10591
Autor:
Fan, Guangpeng, Yan, Fei, Zeng, Xiangquan, Xu, Qingtao, Wang, Ruoyoulan, Zhang, Binghong, Zhou, Jialing, Nan, Liangliang, Wang, Jinhu, Zhang, Zhiwei, Wang, Jia
We have developed the world's first canopy height map of the distribution area of world-level giant trees. This mapping is crucial for discovering more individual and community world-level giant trees, and for analyzing and quantifying the effectiven
Externí odkaz:
http://arxiv.org/abs/2404.14661
Autor:
Wu, Ke, Zhang, Kaizhao, Zhang, Zhiwei, Yuan, Shanshuai, Tie, Muer, Wei, Julong, Xu, Zijun, Zhao, Jieru, Gan, Zhongxue, Ding, Wenchao
Online dense mapping of urban scenes forms a fundamental cornerstone for scene understanding and navigation of autonomous vehicles. Recent advancements in mapping methods are mainly based on NeRF, whose rendering speed is too slow to meet online requ
Externí odkaz:
http://arxiv.org/abs/2403.20159
In this paper, we introduce a new dataset in the medical field of Traumatic Brain Injury (TBI), called TBI-IT, which includes both electronic medical records (EMRs) and head CT images. This dataset is designed to enhance the accuracy of artificial in
Externí odkaz:
http://arxiv.org/abs/2403.09062