Zobrazeno 1 - 10
of 13 666
pro vyhledávání: '"Zhiwu, An"'
The diffusion of deepfake technologies has sparked serious concerns about its potential misuse across various domains, prompting the urgent need for robust detection methods. Despite advancement, many current approaches prioritize short-term gains at
Externí odkaz:
http://arxiv.org/abs/2408.08412
Recently, Role-Playing Agents (RPAs) have garnered increasing attention for their potential to deliver emotional value and facilitate sociological research. However, existing studies are primarily confined to the textual modality, unable to simulate
Externí odkaz:
http://arxiv.org/abs/2408.04203
Autor:
Huang, Ziyuan, Ji, Kaixiang, Gong, Biao, Qing, Zhiwu, Zhang, Qinglong, Zheng, Kecheng, Wang, Jian, Chen, Jingdong, Yang, Ming
This paper introduces Chain-of-Sight, a vision-language bridge module that accelerates the pre-training of Multimodal Large Language Models (MLLMs). Our approach employs a sequence of visual resamplers that capture visual details at various spacial s
Externí odkaz:
http://arxiv.org/abs/2407.15819
Deep networks can usually depend on extracting more structural information to improve denoising results. However, they may ignore correlation between pixels from an image to pursue better denoising performance. Window transformer can use long- and sh
Externí odkaz:
http://arxiv.org/abs/2407.05709
This paper studies the problem of increasing the connectivity of an ad-hoc peer-to-peer network subject to cyber-attacks targeting the agents in the network. The adopted strategy involves the design of local interaction rules for the agents to locall
Externí odkaz:
http://arxiv.org/abs/2406.18467
We propose In-Context Translation (ICT), a general learning framework to unify visual recognition (e.g., semantic segmentation), low-level image processing (e.g., denoising), and conditional image generation (e.g., edge-to-image synthesis). Thanks to
Externí odkaz:
http://arxiv.org/abs/2404.09633
Autor:
Wen, Cheng, Cao, Jialun, Su, Jie, Xu, Zhiwu, Qin, Shengchao, He, Mengda, Li, Haokun, Cheung, Shing-Chi, Tian, Cong
Formal verification provides a rigorous and systematic approach to ensure the correctness and reliability of software systems. Yet, constructing specifications for the full proof relies on domain expertise and non-trivial manpower. In view of such ne
Externí odkaz:
http://arxiv.org/abs/2404.00762
Visual instruction tuning is a key training stage of large multimodal models (LMMs). Nevertheless, the common practice of indiscriminately mixing instruction-following data from various tasks may result in suboptimal overall performance due to differ
Externí odkaz:
http://arxiv.org/abs/2403.04343
In this paper, we investigate the verification and enforcement of strong state-based opacity (SBO) in discrete-event systems modeled as partially-observed (nondeterministic) finite-state automata, including strong K-step opacity (K-SSO), strong curre
Externí odkaz:
http://arxiv.org/abs/2401.10363
Autor:
Li, Xijun, Zhu, Fangzhou, Zhen, Hui-Ling, Luo, Weilin, Lu, Meng, Huang, Yimin, Fan, Zhenan, Zhou, Zirui, Kuang, Yufei, Wang, Zhihai, Geng, Zijie, Li, Yang, Liu, Haoyang, An, Zhiwu, Yang, Muming, Li, Jianshu, Wang, Jie, Yan, Junchi, Sun, Defeng, Zhong, Tao, Zhang, Yong, Zeng, Jia, Yuan, Mingxuan, Hao, Jianye, Yao, Jun, Mao, Kun
In an era of digital ubiquity, efficient resource management and decision-making are paramount across numerous industries. To this end, we present a comprehensive study on the integration of machine learning (ML) techniques into Huawei Cloud's OptVer
Externí odkaz:
http://arxiv.org/abs/2401.05960