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 spatiotemporally redundant and semantically long-tailed. We show that existing…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
