Quantization-Aware Kalman Estimation for Diffusion Sampling

The paper introduces QuAKE, a Quantization-Aware Kalman Estimator designed to correct errors in diffusion model sampling when using quantized denoisers. By treating sampling as an online estimation problem, QuAKE leverages the history of quantized outputs to recover full-precision estimates, updating a posterior in closed form at each step. The method is lightweight, plug‑and‑play, and works with any high‑order multistep ODE sampler, outperforming existing correction techniques on W4A4‑quantized text‑to‑image diffusion models.

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 Computer Vision.

• diffusion
• efficiency