Sik-Ho TsangBrief Review — PaLI-X: On Scaling up a Multilingual Vision and Language ModelPaLI-X, By Scaling Up PaLIJul 4
Fabio MatricardiinGenerative AINanoLlava is the smallest Visual LanguageLet’s discover together how to run it offline on your Computer.May 272
Sik-Ho TsangBrief Review — Florence: A New Foundation Model for Computer VisionFlorence, Pretrained Using Image Captioning DatasetFeb 6Feb 6
Márcio Faustino SantosArt vs EntertainmentTechnologies are the biggest ideologies of all.Jun 13Jun 13
Sik-Ho TsangBrief Review — Florence-2: Advancing a Unified Representation for a Variety of Vision TasksImprove Florence as Florence-2, FLD-5B Dataset is ConstructedMar 7Mar 7
Sik-Ho TsangBrief Review — PaLI-X: On Scaling up a Multilingual Vision and Language ModelPaLI-X, By Scaling Up PaLIJul 4
Fabio MatricardiinGenerative AINanoLlava is the smallest Visual LanguageLet’s discover together how to run it offline on your Computer.May 272
Sik-Ho TsangBrief Review — Florence: A New Foundation Model for Computer VisionFlorence, Pretrained Using Image Captioning DatasetFeb 6
Sik-Ho TsangBrief Review — Florence-2: Advancing a Unified Representation for a Variety of Vision TasksImprove Florence as Florence-2, FLD-5B Dataset is ConstructedMar 7
Sik-Ho TsangBrief Review — Conditional Prompt Learning for Vision-Language ModelsConditional Context Optimization (CoCoOp) is ProposedMay 16
Abang Edwin SAA Semiotic Analysis of Emoji: Understanding the Visual Language of Digital CommunicationAbstract:Mar 28, 2023
Sik-Ho TsangBrief Review — Learning to Prompt for Vision-Language ModelsContext Optimization (CoOp), Improves CLIPMay 9