← Search

Lizhuo Luo

2 accepted papers

2025

DICE: Staleness-Centric Optimizations for Parallel Diffusion MoE Inference

ICCV 2025poster

Mixture-of-Experts-based (MoE-based) diffusion models demonstrate remarkable scalability in high-fidelity image generation, yet their reliance on expert parallelism introduces critical communication bottlenecks. State-of-the-art methods alleviate such overhead in parallel diffusion inference through…