Metraipolis › archive › dc_cd6c2f24f50c
MORCA: Offline-to-Online Reinforcement Learning for Adaptive Cache Reuse in Video Diffusion Acceleration — arXiv:2610.10457
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10457
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:48:12.403Z
- SHA-256 of the archived text
b9ccf07c6385b09ce13508dca4e380af5abaa56213b3940146ce81a9d8113c04- Stable URL of this page
https://metraipolis.com/documento/dc_cd6c2f24f50c
How to cite
MORCA: Offline-to-Online Reinforcement Learning for Adaptive Cache Reuse in Video Diffusion Acceleration — arXiv:2610.10457 — arXiv (en), https://arxiv.org/abs/2610.10457 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd6c2f24f50c (Metraipolis archive dc_cd6c2f24f50c, sha256 b9ccf07c6385b09ce13508dca4e380af5abaa56213b3940146ce81a9d8113c04)
BibTeX
@misc{dccd6c2f24f50c,
title = {MORCA: Offline-to-Online Reinforcement Learning for Adaptive Cache Reuse in Video Diffusion Acceleration — arXiv:2610.10457},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10457},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd6c2f24f50c; sha256 b9ccf07c6385b09ce13508dca4e380af5abaa56213b3940146ce81a9d8113c04},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10457. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Diffusion Transformers (DiTs) achieve remarkable performance in video synthesis, but their iterative denoising process suffers from high inference latency. To address this, caching has emerged as an effective acceleration strategy by capitalizing on inter-step redundancy during denoising. Existing dynamic caching methods typically estimate the error that cache reuse would introduce at each denoising step (step error) to guide cache decisions, whereas our concern is how much quality loss cache reuse would cause in the final generated video (terminal error). We show that step error does not directly correspond to terminal error and that latent information helps capture their relationship, thereby informing cache decisions. Moreover, existing threshold-based methods cannot provide precise speedup control, making it difficult to meet practical requirements for user-specified acceleration targets. To address these limitations, we introduce MORCA, a cache scheduling framework trained through offline-to-online reinforcement learning to make latent-aware reuse/recompute decisions under user-specified acceleration targets. Extensive experiments on different video generation models across multiple target acceleration ratios demonstrate that MORCA achieves better generation fidelity than state-of-the-art caching methods under comparable computational budgets. Code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.10457 — 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 2026-10-08T12:18:15.503Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).