SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features Paper β’ 2502.14786 β’ Published 7 days ago β’ 117
AIMv2 Collection A collection of AIMv2 vision encoders that supports a number of resolutions, native resolution, and a distilled checkpoint. β’ 19 items β’ Updated Nov 22, 2024 β’ 73
view article Article Training and Finetuning Embedding Models with Sentence Transformers v3 May 28, 2024 β’ 188