Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization.

Shuo Xing, Peiran Li, Yuping Wang, Ruizheng Bai, Yueqi Wang, Chan-Wei Hu, Chengxuan Qian, Huaxiu Yao, Zhengzhong Tu

Browse the full EMNLP paper archive.