BudCache optimizes step cache policies for a fixed inference budget in diffusion models via combinatorial search, outperforming threshold heuristics in quality on FLUX.1-dev and Wan2.1.
Learning to discretize denoising diffusion odes
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Under a Gaussian prior assumption, zero-shot diffusion posterior samplers for inverse problems admit closed-form spectral representations that enable a new parameter-selection framework balancing perceptual quality and signal fidelity.
Derives discretization error bounds and input-to-state stability guarantees for SS-NOs and FNOs, with empirical validation on 1D and 2D PDE benchmarks.
citing papers explorer
-
Budget-Constrained Step-Level Diffusion Caching
BudCache optimizes step cache policies for a fixed inference budget in diffusion models via combinatorial search, outperforming threshold heuristics in quality on FLUX.1-dev and Wan2.1.