Metraipolis › archive › dc_35d06d38fe38
Any Forcing: Any-Step Generality and One-Step Stability for Autoregressive Video Generation — arXiv:2610.42031
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.42031
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T05:46:35.232Z
- SHA-256 of the archived text
07cbb5eae9e344997b48e5a87e5c65fc833efaa5c706c0ba7e035f29ce182099- Stable URL of this page
https://metraipolis.com/documento/dc_35d06d38fe38
How to cite
Any Forcing: Any-Step Generality and One-Step Stability for Autoregressive Video Generation — arXiv:2610.42031 — arXiv (en), https://arxiv.org/abs/2610.42031 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_35d06d38fe38 (Metraipolis archive dc_35d06d38fe38, sha256 07cbb5eae9e344997b48e5a87e5c65fc833efaa5c706c0ba7e035f29ce182099)
BibTeX
@misc{dc35d06d38fe38,
title = {Any Forcing: Any-Step Generality and One-Step Stability for Autoregressive Video Generation — arXiv:2610.42031},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.42031},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_35d06d38fe38; sha256 07cbb5eae9e344997b48e5a87e5c65fc833efaa5c706c0ba7e035f29ce182099},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.42031. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Autoregressive video generation enables efficient inference through streaming prediction. However, existing methods are typically restricted to fixed sampling steps, limiting the flexibility to balance generation quality and efficiency, while one-step generation suffers from degraded visual quality and error accumulation over long sequences, leading to content drift and generation collapse. To address these issues, we propose Any Forcing, a unified framework for achieving Any-Step Generality and One-Step Stability. Specifically, we introduce a unified adversarial discriminator that jointly performs real-distribution alignment, inter-step consistency alignment, and first-frame quality enhancement, enabling flexible sampling while preserving one-step generation quality. Furthermore, we propose a training-free adaptive long-term memory selection mechanism that selects historical states based on global semantic relevance and local value contribution, while remapping their temporal positions to preserve temporal relationships within the memory cache, thereby enabling stable one-step long-video generation. Experiments demonstrate that Any Forcing achieves high-quality and stable one-step autoregressive video generation, achieving 20.9 FPS and 24.7 FPS for short and long video generation on a single H100 GPU, respectively. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.42031 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T05:33:32.324Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).