Author name: Honghao Fu, Miao Xu, Yiwei Wang, Dailing Zhang, Liu Jun, Yujun Cai

arXiv:2604.05418v2 Announce Type: replace
Abstract: Scaling multimodal large language models (MLLMs) to long videos is constrained by limited context windows. While retrieval-augmented generation (RAG) is a promising remedy by organizing query-relevan…

arXiv:2604.05418v1 Announce Type: new
Abstract: Scaling multimodal large language models (MLLMs) to long videos is constrained by limited context windows. While retrieval-augmented generation (RAG) is a promising remedy by organizing query-relevant vi…