ViPE: Visual Perception in Parameter Space for Efficient Video-Language Understanding EMNLP

Shichen Lu | Tongtian Yue | Longteng Guo | Handong Li | Xingjian He | Si Liu | Jing Liu |

VRoPE: Rotary Position Embedding for Video Large Language Models EMNLP

Zikang Liu | Longteng Guo | Yepeng Tang | Tongtian Yue | Junxian Cai | Kai Ma | Qingbin Liu | Xi Chen | Jing Liu |