Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation
机构 * Sun Yat-sen University(中山大学) ; ByteDance Intelligent Creation(字节跳动智能创作) ; ByteDance Seed Vision(字节跳动种子视觉) ; Guangdong Province Key Laboratory of Information Security Technology(广东省信息安全技术重点实验室) ; Pazhou Lab (Huangpu)(琶洲实验室(黄埔))
专题命中 扩散模型 :image generation(title,abstract);text-to-image(title,abstract);diffusion(title,abstract);分类 cs.CV
Comments Accepted by ICCV 2025