Preprint Open access
Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE
Mixture-of-Experts (MoE), popularized by large language models, is a promising paradigm for scaling visual generative models. However, conventional token-wise MoE routes tokens independently within a homogeneous expert pool and regularizes expert usage toward uniformity, making it poorly matched to video data that is s …