Bootstrap Your Generator: Unpaired Visual Editing with Flow Matching 事件

Bootstrap Your Generator: Unpaired Visual Editing with Flow Matching arXiv:2606.03911v1 Announce Type: new Abstract: Modern generative models possess a deep understanding of visual content, yet training them for image editing typically requires massive datasets of paired examples. This limits scalability, especially for video editing where collecting paired data is prohibitively expensive. We propose Bootstrap Your Generator (ByG), a general framework for unpaired training of flow matching edit