From 3f6ab2cd50b652cdb9ef177bb1ddc177577e6d30 Mon Sep 17 00:00:00 2001 From: Jiaqi Han Date: Sun, 1 Mar 2026 23:37:43 -0800 Subject: [PATCH] update --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 293a0b3..6726a25 100644 --- a/README.md +++ b/README.md @@ -16,7 +16,7 @@ Jiaqi Han* $^1$, Juntong Shi* $^1$, Puheng Li $^1$, Haotian Ye $^1$, Qiushan Guo ## 🎯 Overview -we propose *Spectrum*, a training-free spectral diffusion feature forecaster that enables global, long-range feature reuse with tightly controlled error. We view the latent features of the denoiser as functions over time and approximate them with Chebyshev polynomials. Specifically, we fit the coefficient for each basis via ridge regression, which is then leveraged to forecast features at multiple future diffusion steps. We theoretically reveal that our approach admits more favorable long-horizon behavior and yields an error bound that does not compound with the step size. +We propose *Spectrum*, a training-free *spectral* diffusion feature forecaster that enables global, long-range feature reuse with tightly controlled error. We view the latent features of the denoiser as functions over time and approximate them with *Chebyshev polynomials*. Specifically, we fit the coefficient for each basis via ridge regression, which is then leveraged to forecast features at multiple future diffusion steps. We theoretically reveal that our approach admits more favorable long-horizon behavior and yields an error bound that does not compound with the step size. Extensive experiments on various state-of-the-art image and video diffusion models consistently verify the superiority of our approach. Notably, we achieve up to $4.79\times$ speedup on FLUX.1 and $4.67\times$ speedup on Wan2.1-14B, while maintaining much higher sample quality compared with the baselines.