BI, Hanbo; YUAN, Zhiqiang; JIA, Zexi; ZHANG, Jiapei; LI, Chongyang; LUO, Peixiang; DENG, Ying; DUAN, Xiaoyue; ZHANG, Jinchao. F2RVLM: Boosting Fine-grained Fragment Retrieval for Multi-Modal Long-form Dialogue with Vision Language Model. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 17, p. 14493–14501, 2026. DOI: 10.1609/aaai.v40i17.38466. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/38466. Acesso em: 26 may. 2026.