Zhang Y, Liu Y, Guo Z, Zhang Y, Yang X, Zhang X, et al. LLaVA-UHD v2: Exploiting Hierarchical Vision Granularity in MLLMs via Inverse Semantic Pyramid. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 28];40(15):12934-42. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/38292