QIAO, Yuming et al. Aligning Cross-View Visual Geometries in LVLMs Through Human-Like Reasoning Learning. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 23, p. 19345–19353, 2026. DOI: 10.1609/aaai.v40i23.39011. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/39011. Acesso em: 16 may. 2026.