Výsledky vyhledávání

Report

Do Pre-trained Vision-Language Models Encode Object States?

Autor: Newman, Kaleb, Wang, Shijie, Zang, Yuan, Heffren, David, Sun, Chen

For a vision-language model (VLM) to understand the physical world, such as cause and effect, a first step is to capture the temporal dynamics of the visual world, for example how the physical states of objects evolve over time (e.g. a whole apple in

Externí odkaz: http://arxiv.org/abs/2409.10488

Zobrazit plný text záznamu

Report

Pre-trained Vision-Language Models Learn Discoverable Visual Concepts

Autor: Zang, Yuan, Yun, Tian, Tan, Hao, Bui, Trung, Sun, Chen

Do vision-language models (VLMs) pre-trained to caption an image of a "durian" learn visual concepts such as "brown" (color) and "spiky" (texture) at the same time? We aim to answer this question as visual concepts learned "for free" would enable wid

Externí odkaz: http://arxiv.org/abs/2404.12652

Zobrazit plný text záznamu

Akademický článek

Batch production of centimeter-scale monolayer MoS2 with low nucleation by face-to-face metal precursor supply

Autor: Li, Lianbi, Wang, Lihan, Ding, Binbin, Yan, Denghui, Li, Zelong, Ren, Xiaolong, Zang, Yuan, Feng, Song, Li, Zebin, Zhang, Guoqing, Fang, Qinglong, Xia, Caijuan

Publikováno v: In Vacuum August 2024 226

Zobrazit plný text záznamu

Report

Learning to Attack: Towards Textual Adversarial Attacking in Real-world Situations

Autor: Zang, Yuan, Hou, Bairu, Qi, Fanchao, Liu, Zhiyuan, Meng, Xiaojun, Sun, Maosong

Adversarial attacking aims to fool deep neural networks with adversarial examples. In the field of natural language processing, various textual adversarial attack models have been proposed, varying in the accessibility to the victim model. Among them

Externí odkaz: http://arxiv.org/abs/2009.09192

Zobrazit plný text záznamu

Report

OpenAttack: An Open-source Textual Adversarial Attack Toolkit

Autor: Zeng, Guoyang, Qi, Fanchao, Zhou, Qianrui, Zhang, Tingji, Ma, Zixian, Hou, Bairu, Zang, Yuan, Liu, Zhiyuan, Sun, Maosong

Textual adversarial attacking has received wide and increasing attention in recent years. Various attack models have been proposed, which are enormously distinct and implemented with different programming frameworks and settings. These facts hinder q

Externí odkaz: http://arxiv.org/abs/2009.09191

Zobrazit plný text záznamu

Report

Word-level Textual Adversarial Attacking as Combinatorial Optimization

Autor: Zang, Yuan, Qi, Fanchao, Yang, Chenghao, Liu, Zhiyuan, Zhang, Meng, Liu, Qun, Sun, Maosong

Adversarial attacks are carried out to reveal the vulnerability of deep neural networks. Textual adversarial attacking is challenging because text is discrete and a small perturbation can bring significant change to the original input. Word-level att

Externí odkaz: http://arxiv.org/abs/1910.12196

Zobrazit plný text záznamu