In this article, we use transfer learning with I-JEPA model for image classification. We add a simple Linear layer classifier on top of the frozen backbone. ...

In this article, we use a pretrained I-JEPA model for image similarity. We specifically use the ViT-H I-JEPA trained with 14x14 patches. ...

In this article, we cover the introduction to I-JEPA. We start with what is I-JEPA, why we need it, its architecture, evaluation results, and comparison with other similar methods. ...

In this article, we build a simple video summarizer application using Qwen2.5-Omni 3B model with the UI powered by Gradio. ...

In this article, we cover the introduction to BAGEL, an unified multimodal model for image generation, image editing, and free-form image manipulation with non-thinking and thinking capabilties. ...