Metraipolis › archive › dc_d013efa86379

Vorch-Director: Interactive World Story Model via Noise-Aware Error Rectification — arXiv:2608.05776

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.05776
License (as archived)
CC0-1.0
Archived
2026-10-31T10:36:14.156Z
SHA-256 of the archived text
3db9ff8aa42940ae5b39989a7fb8d72c7770b478218d231fe43b8fedae46fcb0
Stable URL of this page
https://metraipolis.com/documento/dc_d013efa86379

How to cite

Vorch-Director: Interactive World Story Model via Noise-Aware Error Rectification — arXiv:2608.05776 — arXiv (en), https://arxiv.org/abs/2608.05776 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d013efa86379 (Metraipolis archive dc_d013efa86379, sha256 3db9ff8aa42940ae5b39989a7fb8d72c7770b478218d231fe43b8fedae46fcb0)
BibTeX
@misc{dcd013efa86379,
  title = {Vorch-Director: Interactive World Story Model via Noise-Aware Error Rectification — arXiv:2608.05776},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.05776},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d013efa86379; sha256 3db9ff8aa42940ae5b39989a7fb8d72c7770b478218d231fe43b8fedae46fcb0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05776. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autoregressive continuation provides a natural path toward minute-scale audio-visual generation by repeatedly extending a short-window generator conditioned on previously generated video and audio. However, models are trained on clean ground-truth histories, while inference relies on their own generated histories, where accumulated errors cause identity drift, over-smoothing, and audio-visual desynchronization. Recent methods reduce this mismatch by reusing prediction residuals as synthetic corruption, but we observe that the effectiveness of residual correction critically depends on the flow-matching noise level at which residuals are produced. We propose Vorch-Director, a noise-level-aware residual correction strategy that associates each residual with its originating noise level and injects residuals from matched noise regimes during training. By aligning injected errors with the denoising process, Vorch-Director produces more realistic autoregressive histories while retaining efficient teacher-forcing training. Built on the audio-visual LTX-2 diffusion transformer, Vorch-Director further introduces task embeddings to distinguish historical video, reference images, and target video, enabling unified conditioning for long-horizon generation. Together with a clean conditioning sink and mixed-task training, Vorch-Director supports multi-shot, multi-subject, reference-guided audio-visual long-video generation. We evaluate Vorch-Director on ST-Bench and introduce a new long-horizon audio-visual benchmark with metrics for quality drift and long-range consistency. Extensive experiments demonstrate improved stability and audio-visual fidelity over strong baselines.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.05776 — 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 2026-10-31T10:23:31.014Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).