Metraipolis › archive › dc_4e6380d6ea22

JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion — arXiv:2608.03974

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.03974
License (as archived): CC0-1.0
Archived: 2026-10-31T12:59:53.322Z
SHA-256 of the archived text: d6582bfd5aee2e1266c224ba17d96cfcf55b05f97d3d35b1d0757c0fbfc4183d
Stable URL of this page: https://metraipolis.com/documento/dc_4e6380d6ea22

How to cite

JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion — arXiv:2608.03974 — arXiv (en), https://arxiv.org/abs/2608.03974 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e6380d6ea22 (Metraipolis archive dc_4e6380d6ea22, sha256 d6582bfd5aee2e1266c224ba17d96cfcf55b05f97d3d35b1d0757c0fbfc4183d)

BibTeX

@misc{dc4e6380d6ea22,
  title = {JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion — arXiv:2608.03974},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03974},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e6380d6ea22; sha256 d6582bfd5aee2e1266c224ba17d96cfcf55b05f97d3d35b1d0757c0fbfc4183d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03974. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Real-time video editing requires low-latency causal generation with bounded computational resources while preserving source fidelity and long-term temporal consistency. We present JoyAI-Video-Edit, a 16B-parameter autoregressive diffusion framework for real-time, open-ended video editing without access to future frames or a predefined video duration. Our method combines chunk-wise autoregressive adaptation, Source-Anchored Distribution Matching Distillation (SA-DMD), and Long-Horizon Autoregressive Distillation to reduce train--inference mismatch, preserve source fidelity during two-step generation, and mitigate accumulated temporal drift. Extensive automatic and human evaluations show that JoyAI-Video-Edit substantially outperforms existing streaming editors and remains competitive with strong offline systems on both short and long videos. The complete system achieves end-to-end 720p video editing at approximately 30 FPS on a single Nvidia B200 GPU. Code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-05 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.03974 — 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 2026-10-31T12:45:33.288Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).