Zobrazeno 1 - 10
of 91
pro vyhledávání: '"Wu, Yuanwei"'
GPT-4V has attracted considerable attention due to its extraordinary capacity for integrating and processing multimodal information. At the same time, its ability of face recognition raises new safety concerns of privacy leakage. Despite researchers'
Externí odkaz:
http://arxiv.org/abs/2407.16686
Existing work on jailbreak Multimodal Large Language Models (MLLMs) has focused primarily on adversarial examples in model inputs, with less attention to vulnerabilities, especially in model API. To fill the research gap, we carry out the following w
Externí odkaz:
http://arxiv.org/abs/2311.09127
Autor:
Yang, Wenjin, Wu, Yuanwei, Gong, Yan, Mauron, Nicolas, Zhang, Bo, Menten, Karl M., Mai, Xiaofeng, Liu, Dejian, Li, Juan, Li, Jingjing
Studying stars that are located off the Galactic plane is important for understanding the formation history of the Milky Way. We searched for SiO masers toward off-plane O-rich asymptotic giant branch (AGB) stars from the catalog presented by Mauron
Externí odkaz:
http://arxiv.org/abs/2310.13489
A 22 GHz water maser survey was conducted towards 178 O-rich AGB stars with the aim of identifying maser emission associated with the Sagittarius stellar stream. In this survey, maser emissions were detected in 21 targets, of which 20 were new detect
Externí odkaz:
http://arxiv.org/abs/2207.05914
Publikováno v:
Hangkong bingqi, Vol 31, Iss 1, Pp 58-65 (2024)
When air-to-air missile strikes low and ultra-low altitude targets, the performance of missile-borne radar to distinguish targets and clutter is reduced. In this paper, aiming at the problem of target recognition of missile-borne radar, multiple targ
Externí odkaz:
https://doaj.org/article/141455f6673c4bac97e143527dfdd982
Autor:
Li, Yingjie, Xu, Ye, Li, JingJing, Wu, Yuanwei, Bian, Shaibo, Lin, ZeHao, Yang, WenJin, Hao, Chaojie, Liu, DeJian
We measured the relative positions between two pairs of compact extragalactic sources (CESs), J1925-2219 \& J1923-2104 (C1--C2) and J1925-2219 \& J1928-2035 (C1--C3) on 2020 October 23--25 and 2021 February 5 (totaling four epochs), respectively, usi
Externí odkaz:
http://arxiv.org/abs/2111.14095
In this paper, we propose BPGrad, a novel approximate algorithm for deep nueral network training, based on adaptive estimates of feasible region via branch-and-bound. The method is based on the assumption of Lipschitz continuity in objective function
Externí odkaz:
http://arxiv.org/abs/2104.01730
In this paper, we investigate the empirical impact of orthogonality regularization (OR) in deep learning, either solo or collaboratively. Recent works on OR showed some promising results on the accuracy. In our ablation study, however, we do not obse
Externí odkaz:
http://arxiv.org/abs/2001.01275
Publikováno v:
Pattern Recognition 2019
This paper proposes an innovative object detector by leveraging deep features learned in high-level layers. Compared with features produced in earlier layers, the deep features are better at expressing semantic and contextual information. The propose
Externí odkaz:
http://arxiv.org/abs/1912.04514
In this chapter, we present a brief overview of the recent development in object detection using convolutional neural networks (CNN). Several classical CNN-based detectors are presented. Some developments are based on the detector architectures, whil
Externí odkaz:
http://arxiv.org/abs/1912.01844