Generated Content
Generated content (AIGC), encompassing AI-produced text, images, and video, is a rapidly evolving field focused on developing and evaluating methods for creating and identifying such content. Current research emphasizes improving the quality and realism of AIGC, developing robust detection methods to mitigate misuse (often employing techniques like CLIP and diffusion models), and exploring ethical considerations such as copyright and bias. This area is significant due to its potential to revolutionize creative industries and its implications for misinformation, intellectual property, and the broader societal impact of AI.
Papers
Towards Defining an Efficient and Expandable File Format for AI-Generated Contents
Yixin Gao, Runsen Feng, Xin Li, Weiping Li, Zhibo Chen
LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models
Junyan Ye, Baichuan Zhou, Zilong Huang, Junan Zhang, Tianyi Bai, Hengrui Kang, Jun He, Honglin Lin, Zihao Wang, Tong Wu, Zhizheng Wu, Yiping Chen, Dahua Lin, Conghui He, Weijia Li