作者位次 #2/8ICLR 2026Poster· Computer Vision / Vision Models & Multimodal
Memento: Toward an All-Day Proactive Assistant for Ultra-Long Streaming Video
Hongxiang Jiang · Zengrui Ge · Guo Chen · Qixiong Wang · Jile Jiao · Xuetao Feng · Yuan Wang · Yan Wang
多模态OpenReview