Improving Visual Representation Alignment Generation with GRPO 事件

Improving Visual Representation Alignment Generation with GRPO arXiv:2606.00583v1 Announce Type: new Abstract: Recent diffusion transformers have demonstrated strong image synthesis capabilities but remain inefficient to train due to weak alignment between generative and discriminative representations. While representation alignment frameworks such as REPA improve convergence by aligning noisy denoising features with pretrained visual encoders, their externally supervised alignment loss is stat