Saved in:
Bibliographic Details
Main Authors: Yu, Zhengyang, Hayakawa, Akio, Ishii, Masato, Yu, Qingtao, Shibuya, Takashi, Zhang, Jing, Mitsufuji, Yuki
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.11203
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Autoregressive video diffusion models (AR-VDMs) show strong promise as scalable alternatives to bidirectional VDMs, enabling real-time and interactive applications. Yet there remains room for improvement in their sample fidelity. A promising solution is inference-time alignment, which optimizes the noise space to improve sample fidelity without updating model parameters. Yet, optimization- or search-based methods are computationally impractical for AR-VDMs. Recent text-to-image (T2I) works address this via feedforward noise refiners that modulate sampled noises in a single forward pass. Can such noise refiners be extended to AR-VDMs? We identify the failure of naively extending T2I noise refiners to AR-VDMs and propose AutoRefiner-a noise refiner tailored for AR-VDMs, with two key designs: pathwise noise refinement and a reflective KV-cache. Experiments demonstrate that AutoRefiner serves as an efficient plug-in for AR-VDMs, effectively enhancing sample fidelity by refining noise along stochastic denoising paths.