光明实验室大数据智能处理与分析团队三篇论文被人工智能领域顶级国际会议接收
论文1：
Privacy-Shielded Image Compression: Defending Against Exploitation from Vision-Language Pretrained Models (ICML2025)
论文2：
Prompt-Guided Alignment with Information Bottleneck Makes Image Compression Also a Restorer (NeurIPS2025)
论文3：
End-to-End Low-Light Enhancement for Object Detection with Learned Metadata from RAWs (NeurIPS2025)
中文
EN
