AI推介-多模态视觉语言模型VLMs论文速览(arXiv方向):2024.04.15-2024.04.25
文章目录~1.AutoGluon-Multimodal(AutoMM):SuperchargingMultimodalAutoMLwithFoundationModels2.FusionofDomain-AdaptedVisionandLanguageModelsforMedicalVisualQuestionAnswering3.CatLIP:CLIP-levelVisualRecognitio