{"ID":2829660,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.11203","arxiv_id":"2512.11203","title":"AutoRefiner: Improving Autoregressive Video Diffusion Models via Reflective Refinement Over the Stochastic Sampling Path","abstract":"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.","short_abstract":"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 impro...","url_abs":"https://arxiv.org/abs/2512.11203","url_pdf":"https://arxiv.org/pdf/2512.11203v2","authors":"[\"Zhengyang Yu\",\"Akio Hayakawa\",\"Masato Ishii\",\"Qingtao Yu\",\"Takashi Shibuya\",\"Jing Zhang\",\"Yuki Mitsufuji\"]","published":"2025-12-12T01:28:22Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}