Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
SelfLift: Accelerating Few-Step Diffusion via Self-Recovering Resolution Transition
Tingyan Wen, Chenqian Yan, Xurui Peng +4
Few-step diffusion models substantially compress temporal computation, making the spatial cost of each model evaluation an increasingly dominant source of inference latency. Progre…
cs.CV2025
No Cache Left Idle: Accelerating diffusion model via Extreme-slimming Caching
Tingyan Wen, Haoyu Li, Yihuang Chen +3
Diffusion models achieve remarkable generative quality, but computational overhead scales with step count, model depth, and sequence length. Feature caching is effective since adja…