Zhang, Yipeng, Yifan Liu, Zonghao Guo, Yidan Zhang, Xuesong Yang, Xiaoying Zhang, Chi Chen, et al. “LLaVA-UHD v2: Exploiting Hierarchical Vision Granularity in MLLMs via Inverse Semantic Pyramid”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 15 (March 14, 2026): 12934–12942. Accessed May 28, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/38292.