KIM, Geewook; SEO, Minjoon. State-Space Hierarchical Compression with Gated Attention and Learnable Sampling for Hour-Long Video Understanding in Large Multimodal Models. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 7, p. 5656–5664, 2026. DOI: 10.1609/aaai.v40i7.37485. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/37485. Acesso em: 25 may. 2026.