The year 2024 is expected to be a significant one for multimodal machine learning, with advancements in real-time text-to-image models and open-world vocabulary models. Contrastive language image pretraining (CLIP) has been at the heart of many of these advances since its introduction by OpenAI in 2021. CLIP aligns a vision encoder and a text encoder, enabling the model to understand both visual and natural language inputs. While OpenAI's CLIP model is well-known, there are other important data-centric advances in contrastive language-image pretraining that have improved upon its performance. These include ALIGN, K-LITE, OpenCLIP, MetaCLIP, and DFN. Each of these advances has contributed to the development of more effective multimodal machine learning models, with potential applications ranging from image classification to data filtering networks.