Accelerating Diffusion Transformers with Gaussian Process Rectified Feature Cache
Read the original on arXiv Machine Learning →The paper introduces GP-Refiner, a plug‑and‑play framework that uses Gaussian Process Regression to correct feature predictions in Diffusion Transformers. By observing that residuals between cached and full‑compute features follow a local zero‑mean Gaussian distribution, the method treats cached features as noisy observations of the true trajectory, enabling online correction without needing explicit labels. Experiments show that integrating GP‑Refiner with existing acceleration techniques, such as TaylorSeer, cuts computational load by 19.3% while improving image quality metrics (PSNR +0.9 dB, LPIPS 0.46→0.29).
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.