Xu R, Wang Y, Luo Y, Du B. Rethinking Visual Token Reduction in LVLMs Under Cross-Modal Misalignment. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 14];40(32):27323-31. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/39949