Metraipolis › archive › dc_2142efe47a01

The Past Frames the Future: Memory for Autoregressive Video Generation — arXiv:2609.28466

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.28466
License (as archived)
CC0-1.0
Archived
2026-10-08T12:35:26.195Z
SHA-256 of the archived text
e317084576e2e190b1e7dfe61cb9671865cd8c7108827ca1653ef7c39f5c1e6e
Stable URL of this page
https://metraipolis.com/documento/dc_2142efe47a01

How to cite

The Past Frames the Future: Memory for Autoregressive Video Generation — arXiv:2609.28466 — arXiv (en), https://arxiv.org/abs/2609.28466 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2142efe47a01 (Metraipolis archive dc_2142efe47a01, sha256 e317084576e2e190b1e7dfe61cb9671865cd8c7108827ca1653ef7c39f5c1e6e)
BibTeX
@misc{dc2142efe47a01,
  title = {The Past Frames the Future: Memory for Autoregressive Video Generation — arXiv:2609.28466},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.28466},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2142efe47a01; sha256 e317084576e2e190b1e7dfe61cb9671865cd8c7108827ca1653ef7c39f5c1e6e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28466. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Advances in generative models have improved video fidelity, enabling long-horizon generation, interactive world modeling, and evolving visual environments. Autoregressive (AR) video generation extends visual sequences through causal rollouts. However, a fundamental bottleneck emerges: as the generated sequence expands, practical models must operate under strictly bounded context windows, storage, and computational limits. Consequently, critical historical information, e.g., entity identities, dynamic states, and intervention-induced causal changes, often leaves the active context long before its relevance diminishes. Overcoming this limitation and maintaining temporal persistence constitutes a fundamental memory problem. We present a systematic and comprehensive review of memory mechanisms in AR video generation. We formulate memory operationally as persistent historical information maintained across outer AR steps, capable of influencing future generation even after the originating evidence is no longer locally accessible. Building upon this unified framework, we organize the literature through five complementary perspectives: (I) Forms, the representational carriers of history; (II) Functions, the specific semantic and physical information requiring preservation; (III) Operations, the lifecycle of writing, reading, updating, managing, and integrating memory; (IV) Learning, the optimization of memory behaviors under closed-loop rollouts; and (V) Evaluation, the paradigms for diagnosing genuine memory capabilities. We conclude by synthesizing open challenges, including composable and resource-aware memory architectures, trustworthy state updating, self-rollout learning, and standardized evaluation. By bridging representations, mechanisms, and learning paradigms, this paper establishes a structured foundation for developing reliable, memory-conditioned video generation systems.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-24 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.28466 — 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 2026-10-08T12:12:35.823Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).