作者位次 #4/9AAAI 2026Poster· Artificial Intelligence
F2RVLM: Boosting Fine-grained Fragment Retrieval for Multi-Modal Long-form Dialogue with Vision Language Model
Hanbo Bi · Zhiqiang Yuan · Zexi Jia · Jiapei Zhang · Chongyang Li · Peixiang Luo · Ying Deng · Xiaoyue Duan · Jinchao Zhang