Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE
[Widzenie komputerowe] Autorzy: Yu Xu, Yuxin Zhang, Xiao Yang i 7 więcej
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 visual MoEs fall into a uniformity trap: semantically under-organized routing, compounded by uniform expert-usage regularization, scatters coherent patches across disparate experts, causing routing fragmentation and structural distortion. To address this, we propose SplitMoE, a split-role sparse architecture that breaks the shackles of uniformity. To accommodate the inherent semantic imbalance, we explicitly bifurcate the expert pool into semantic experts and generic experts, with semantic expert…
- Kategoria arxiv
- cs.CV
- Kategoria
- Widzenie komputerowe