Book
Jul 2026
Look Clearly Before Answering: Mitigating Hallucinations in Large Vision-Language Models via Saliency-Driven Perceptual Realignment
This work proposes Saliency-Driven Perceptual Realignment (SDPR), a training-free framework that mitigates the degradation of visual awareness throughout inference and is robust against hallucinations due to its holistic alignment of visual awareness across the entire generative trajectory.
Peng-Xu Chen, Yao Zhu, Guang-Ming Zhu et al.
· Proceedings of the 34th ACM... · 0 citations