Zobrazeno 1 - 10
of 477
pro vyhledávání: '"ZHANG Xuanyu"'
Autor:
Zhang, Xuanyu, Tang, Zecheng, Xu, Zhipei, Li, Runyi, Xu, Youmin, Chen, Bin, Gao, Feng, Zhang, Jian
With the rapid growth of generative AI and its widespread application in image editing, new risks have emerged regarding the authenticity and integrity of digital content. Existing versatile watermarking approaches suffer from trade-offs between tamp
Externí odkaz:
http://arxiv.org/abs/2412.01615
Autor:
Shi, Guangyuan, Lu, Zexin, Dong, Xiaoyu, Zhang, Wenlong, Zhang, Xuanyu, Feng, Yujie, Wu, Xiao-Ming
Aligning large language models (LLMs) through fine-tuning is essential for tailoring them to specific applications. Therefore, understanding what LLMs learn during the alignment process is crucial. Recent studies suggest that alignment primarily adju
Externí odkaz:
http://arxiv.org/abs/2410.17875
The rapid development of generative AI is a double-edged sword, which not only facilitates content creation but also makes image manipulation easier and more difficult to detect. Although current image forgery detection and localization (IFDL) method
Externí odkaz:
http://arxiv.org/abs/2410.02761
Autor:
Luo, Xianzhen, Wang, Yixuan, Zhu, Qingfu, Zhang, Zhiming, Zhang, Xuanyu, Yang, Qing, Xu, Dongliang, Che, Wanxiang
The rapid growth in the parameters of large language models (LLMs) has made inference latency a fundamental bottleneck, limiting broader application of LLMs. Speculative decoding represents a lossless approach to accelerate inference through a guess-
Externí odkaz:
http://arxiv.org/abs/2408.08696
Autor:
Wang, Yixuan, Luo, Xianzhen, Wei, Fuxuan, Liu, Yijun, Zhu, Qingfu, Zhang, Xuanyu, Yang, Qing, Xu, Dongliang, Che, Wanxiang
Existing speculative decoding methods typically require additional model structure and training processes to assist the model for draft token generation. This makes the migration of acceleration methods to the new model more costly and more demanding
Externí odkaz:
http://arxiv.org/abs/2406.17404
With the advent of personalized generation models, users can more readily create images resembling existing content, heightening the risk of violating portrait rights and intellectual property (IP). Traditional post-hoc detection and source-tracing m
Externí odkaz:
http://arxiv.org/abs/2405.16596
3D Gaussian Splatting (3DGS) has already become the emerging research focus in the fields of 3D scene reconstruction and novel view synthesis. Given that training a 3DGS requires a significant amount of time and computational cost, it is crucial to p
Externí odkaz:
http://arxiv.org/abs/2405.15118
This paper introduces Hierarchical Image Steganography, a novel method that enhances the security and capacity of embedding multiple images into a single container using diffusion models. HIS assigns varying levels of robustness to images based on th
Externí odkaz:
http://arxiv.org/abs/2405.11523
AI-generated video has revolutionized short video production, filmmaking, and personalized media, making video local editing an essential tool. However, this progress also blurs the line between reality and fiction, posing challenges in multimedia fo
Externí odkaz:
http://arxiv.org/abs/2404.16824
We present Recurrent Drafter (ReDrafter), an advanced speculative decoding approach that achieves state-of-the-art speedup for large language models (LLMs) inference. The performance gains are driven by three key aspects: (1) leveraging a recurrent n
Externí odkaz:
http://arxiv.org/abs/2403.09919