Metraipolis › archive › dc_ce3db4340370
TRAC: Trajectory-aware Reuse and Adaptive Correction for Efficient Autoregressive Video Generation — arXiv:2610.02779
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.02779
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T09:07:12.852Z
- SHA-256 of the archived text
31355644fdd0c4d4d2888619276c00320a27976f2c24d14d3140fa6d132a71bf- Stable URL of this page
https://metraipolis.com/documento/dc_ce3db4340370
How to cite
TRAC: Trajectory-aware Reuse and Adaptive Correction for Efficient Autoregressive Video Generation — arXiv:2610.02779 — arXiv (en), https://arxiv.org/abs/2610.02779 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce3db4340370 (Metraipolis archive dc_ce3db4340370, sha256 31355644fdd0c4d4d2888619276c00320a27976f2c24d14d3140fa6d132a71bf)
BibTeX
@misc{dcce3db4340370,
title = {TRAC: Trajectory-aware Reuse and Adaptive Correction for Efficient Autoregressive Video Generation — arXiv:2610.02779},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.02779},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce3db4340370; sha256 31355644fdd0c4d4d2888619276c00320a27976f2c24d14d3140fa6d132a71bf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.02779. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In this paper, we present trajectory-aware reuse and adaptive correction (TRAC), a training-free framework for efficient autoregressive (AR) video generation. Existing acceleration methods mainly target single-trajectory generation with bidirectional attention. AR video generation, by contrast, sequentially couples chunk-level denoising trajectories. Consequently, approximation errors accumulate and propagate through the generation process. TRAC addresses this challenge with three components, including robust cumulative scheduling (RCS), autoregressive trajectory-aware guidance scheduling (ATGS), and spectral structure correction (SSC). RCS selects cache reuse schedules by cumulative rollout error and cross-chunk/prompt variation. ATGS coordinates CFG refreshes along the global AR trajectory. SSC restores low-frequency structure of the first chunk to correct long-term structural loss. Experiments on SkyReels-V2 and FramePack-F1 show that, compared with existing methods, TRAC achieves both the highest inference efficiency and the best generation quality for AR video generation. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-05 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.02779 — 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 2026-10-06T08:21:44.172Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).