Li Z, Kong C, Yu Y, Wu Q, Jiang X, Cheung N-M, et al. SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 11];40(42):35617-25. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/40873