Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization.
Yang JinKun XuKun XuLiwei ChenChao LiaoJianchao TanQuzhe HuangBin ChenChenyi LeiAn LiuChengru SongXiaoqiang LeiDi ZhangWenwu OuKun GaiYadong MuPublished in: CoRR (2023)
Keyphrases