Metraipolis › archive › dc_193f11ce342e
Video Generation Models: A Survey of Post-Training and Alignment — arXiv:2610.00812
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.00812
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:11:07.123Z
- SHA-256 of the archived text
edcb013a3a8f3ea106822d2499cbeb79961e4767149a654fb12332427b972a98- Stable URL of this page
https://metraipolis.com/documento/dc_193f11ce342e
How to cite
Video Generation Models: A Survey of Post-Training and Alignment — arXiv:2610.00812 — arXiv (en), https://arxiv.org/abs/2610.00812 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_193f11ce342e (Metraipolis archive dc_193f11ce342e, sha256 edcb013a3a8f3ea106822d2499cbeb79961e4767149a654fb12332427b972a98)
BibTeX
@misc{dc193f11ce342e,
title = {Video Generation Models: A Survey of Post-Training and Alignment — arXiv:2610.00812},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.00812},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_193f11ce342e; sha256 edcb013a3a8f3ea106822d2499cbeb79961e4767149a654fb12332427b972a98},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00812. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Video generation has rapidly progressed from short, low-quality clips to high-resolution, long-duration sequences with complex spatiotemporal dynamics. Despite strong generative priors learned through large-scale pretraining, pretrained video models often fail to reliably follow human intent, maintain temporal coherence, or satisfy physical and safety constraints. Compared with image and text generation, alignment in video generation presents unique challenges, including error accumulation over time, motion-appearance coupling, multi-objective trade-offs, and limited supervision for temporal properties. These challenges motivate systematic post-training strategies that adapt pretrained models without retraining them from scratch. In this survey, we present the first comprehensive review of post-training and alignment in video generation models. We frame post-training as a unifying framework and distinguish between implicit alignment and explicit alignment based on how alignment signals are enforced. From this perspective, we organize existing approaches into four broad categories: supervised fine-tuning methods, self-training and distillation methods, preference- and reward-based methods, and inference-time methods. This taxonomy provides a coherent view of how alignment signals shape model behavior across both training and deployment. Beyond methodological advances, we review commonly used datasets, benchmarks, and evaluation practices, and discuss open challenges such as scalable reward design, long-horizon temporal consistency, stability-expressiveness trade-offs, and safety-aware generation. This survey aims to provide a structured conceptual foundation and practical guidance for advancing controllable and reliable video generation models. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.00812 — 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 2026-10-06T10:21:28.110Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).