Kim, Geewook, and Minjoon Seo. “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, vol. 40, no. 7, Mar. 2026, pp. 5656-64, doi:10.1609/aaai.v40i7.37485.