Bi, Hanbo, Zhiqiang Yuan, Zexi Jia, Jiapei Zhang, Chongyang Li, Peixiang Luo, Ying Deng, Xiaoyue Duan, and Jinchao Zhang. 2026. “F2RVLM: Boosting Fine-Grained Fragment Retrieval for Multi-Modal Long-Form Dialogue With Vision Language Model”. Proceedings of the AAAI Conference on Artificial Intelligence 40 (17):14493-501. https://doi.org/10.1609/aaai.v40i17.38466.