Metraipolis › archive › dc_dd7319964be8

Speculative Sampling in Interactive Video Generation — arXiv:2610.20556

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.20556
License (as archived)
CC0-1.0
Archived
2026-10-15T21:46:51.022Z
SHA-256 of the archived text
bc38680bf473acd1ad2088f62f80cd3764cfc8b610eaba616493d230c8c53573
Stable URL of this page
https://metraipolis.com/documento/dc_dd7319964be8

How to cite

Speculative Sampling in Interactive Video Generation — arXiv:2610.20556 — arXiv (en), https://arxiv.org/abs/2610.20556 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dd7319964be8 (Metraipolis archive dc_dd7319964be8, sha256 bc38680bf473acd1ad2088f62f80cd3764cfc8b610eaba616493d230c8c53573)
BibTeX
@misc{dcdd7319964be8,
  title = {Speculative Sampling in Interactive Video Generation — arXiv:2610.20556},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.20556},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dd7319964be8; sha256 bc38680bf473acd1ad2088f62f80cd3764cfc8b610eaba616493d230c8c53573},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20556. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Interactive video generation commonly relies on small bidirectional chunks to reduce response latency. Yet our preliminary experiments show that larger chunks improve video quality and better utilize GPU parallelism, allowing more latents to be sampled with only a modest increase in sampling time. Motivated by these observations, we propose Speculative Sampling, a strategy that combines the modeling power of large bidirectional windows with the low-latency interaction of small ones. It expands the modeling window by appending noise latents as padding and caches the resulting predictions for reuse when the condition remains unchanged. Predictions are delivered incrementally, while the uncommitted future remains replaceable. Our latency analysis shows that this removes the waiting-time lower bound imposed by chunk boundaries, shifting the optimization focus from reducing chunk size to accelerating per-chunk sampling. Bidirectional window size thus becomes a decision variable for jointly optimizing visual quality and sampling time, rather than a necessary constraint on low-latency interaction. This opens a path to serving large bidirectional models in interactive streaming systems without complex streaming post-training.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.HC, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2610.20556 — 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 2026-10-15T21:33:59.702Z dalla pagina https://arxiv.org/list/cs.HC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).