ZHANG, Yipeng et al. LLaVA-UHD v2: Exploiting Hierarchical Vision Granularity in MLLMs via Inverse Semantic Pyramid. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 15, p. 12934–12942, 2026. DOI: 10.1609/aaai.v40i15.38292. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/38292. Acesso em: 28 may. 2026.