Author name: Xiaoyu Wu, Yifei Wang, Tsu-Jui Fu, Liang-Chieh Chen, Zhe Gan, Chen Wei

arXiv:2605.05206v1 Announce Type: new
Abstract: We study outlier tokens in Diffusion Transformers (DiTs) for image generation. Prior work has shown that Vision Transformers (ViTs) can produce a small number of high-norm tokens that attract disproporti…