← Search

Jiayin Xu

2 accepted papers

2025

Privacy-Shielded Image Compression: Defending Against Exploitation from Vision-Language Pretrained Models

ICML 2025poster

The improved semantic understanding of vision-language pretrained (VLP) models has made it increasingly difficult to protect publicly posted images from being exploited by search engines and other similar tools. In this context, this paper seeks to protect users' privacy by implementing defenses at…

Cited by 0SourcePDFScholar
2025

Prompt-Guided Alignment with Information Bottleneck Makes Image Compression Also a Restorer

NeurIPS 2025poster

Learned Image Compression (LIC) models face critical challenges in real-world scenarios due to various environmental degradations, such as fog and rain. Due to the distribution mismatch between degraded inputs and clean training data, well-trained LIC models suffer from reduced compression efficienc…

Cited by 0SourceScholar