Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Three Creates All: You Only Sample 3 Steps
Yuren Cai, Guangyi Wang, Zongqing Li +3
Diffusion models deliver high-fidelity generation but remain slow at inference time due to many sequential network evaluations. We find that standard timestep conditioning becomes…
cs.LG2024
Diffusion Sampling Correction via Approximately 10 Parameters
Guangyi Wang, Wei Peng, Lijiang Li +3
While powerful for generation, Diffusion Probabilistic Models (DPMs) face slow sampling challenges, for which various distillation-based methods have been proposed. However, they t…