SOURCE-LINKED INTELLIGENCE

SelfLift: Accelerating Few-Step Diffusion via Self-Recovering Resolution Transition

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Few-step diffusion models substantially compress temporal computation, making the spatial cost of each model evaluation an increasingly dominant source of inference latency. Progressive-resolution inference reduces this cost by performing early denoising at low resolution and reserving high-resolution computation for refinement. However, existing methods typically lift intermediate latents directly and rely on subsequent steps to absorb the induced distribution mismatch. In the few-step regime, the limited recovery budget leaves these errors as visible artifacts, constraining how late the tran

Read original source ↗ Open in workspace

recordType

paper

region

Global