Zobrazeno 1 - 10
of 71
pro vyhledávání: '"Hu, Yuepeng"'
Visual hallucination (VH) occurs when a multimodal large language model (MLLM) generates responses with incorrect visual details for prompts. Existing methods for generating VH test cases primarily rely on human annotations, typically in the form of
Externí odkaz:
http://arxiv.org/abs/2410.11242
Multimodal large language models (MLLMs) have become the cornerstone of today's generative AI ecosystem, sparking intense competition among tech giants and startups. In particular, an MLLM generates a text response given a prompt consisting of an ima
Externí odkaz:
http://arxiv.org/abs/2407.09050
Generative AI raises many societal concerns such as boosting disinformation and propaganda campaigns. Watermarking AI-generated content is a key technology to address these concerns and has been widely deployed in industry. However, watermarking is v
Externí odkaz:
http://arxiv.org/abs/2407.04086
Autor:
Cheng, Haoran, Peng, Liang, Xia, Linxuan, Hu, Yuepeng, Li, Hengjia, Lu, Qinglin, He, Xiaofei, Wu, Boxi
Significant advancements in video diffusion models have brought substantial progress to the field of text-to-video (T2V) synthesis. However, existing T2V synthesis model struggle to accurately generate complex motion dynamics, leading to a reduction
Externí odkaz:
http://arxiv.org/abs/2406.03215
Watermark has been widely deployed by industry to detect AI-generated images. A recent watermarking framework called \emph{Stable Signature} (proposed by Meta) roots watermark into the parameters of a diffusion model's decoder such that its generated
Externí odkaz:
http://arxiv.org/abs/2405.07145
Several companies--such as Google, Microsoft, and OpenAI--have deployed techniques to watermark AI-generated content to enable proactive detection. However, existing literature mainly focuses on user-agnostic detection. Attribution aims to further tr
Externí odkaz:
http://arxiv.org/abs/2404.04254
Watermark has been widely deployed by industry to detect AI-generated images. The robustness of such watermark-based detector against evasion attacks in the white-box and black-box settings is well understood in the literature. However, the robustnes
Externí odkaz:
http://arxiv.org/abs/2403.15365
Data poisoning attacks spoof a recommender system to make arbitrary, attacker-desired recommendations via injecting fake users with carefully crafted rating scores into the recommender system. We envision a cat-and-mouse game for such data poisoning
Externí odkaz:
http://arxiv.org/abs/2303.14601
Autor:
Peng, Hao, He, YuanPeng, Hu, Yuepeng, Sheng, Siqi, Maitiyasen, Maierhaba, Li, jingfeng, Liu, Yvxuan, Hou, Xinyu, Song, Haizhu, Yi, Jun
Publikováno v:
In Biomedicine & Pharmacotherapy October 2024 179
Autor:
Xie, Xiaochun, Liu, Yang, Yang, Qi, Ma, Xiaojie, Lu, Yingying, Hu, Yuepeng, Zhang, Guofu, Ke, Lu, Tong, Zhihui, Liu, Yuxiu, Xue, Jing, Lu, Guotao, Li, Weiqin
Publikováno v:
In The American Journal of Pathology August 2024 194(8):1494-1510