ICCV
#ComputerVision#EfficiencyImprovement#Pocket#Transformer#LongSequence#SSM (StateSpaceModel)#VideoGeneration/Understandings
Issue Date: 2025-06-26 Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers, Weiming Ren+, arXiv25 Comment元ポスト:https://x.com/wenhuchen/status/1938064510369280136?s=46&t=Y6UuIHB0Lv0IpmFAjlc2-Q ... #ComputerVision#Pretraining#Pocket#LanguageModel#MulltiModal#Admin'sPick
Issue Date: 2025-06-29 Sigmoid Loss for Language Image Pre-Training, Xiaohua Zhai+, ICCV23 CommentSigLIP論文 ...
Issue Date: 2025-06-26 Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers, Weiming Ren+, arXiv25 Comment元ポスト:https://x.com/wenhuchen/status/1938064510369280136?s=46&t=Y6UuIHB0Lv0IpmFAjlc2-Q ... #ComputerVision#Pretraining#Pocket#LanguageModel#MulltiModal#Admin'sPick
Issue Date: 2025-06-29 Sigmoid Loss for Language Image Pre-Training, Xiaohua Zhai+, ICCV23 CommentSigLIP論文 ...