Metraipolis › archive › dc_72f331dd3bb9

XYZFlow:Scaling Multi dimensional Shortcut Flows for Efficient Generative Modeling — arXiv:2608.12276

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.12276
License (as archived): CC0-1.0
Archived: 2026-10-19T05:49:44.395Z
SHA-256 of the archived text: f6201203d8441f008b19bec36609e510630a1ac30bab15320f2ffbb408df0f25
Stable URL of this page: https://metraipolis.com/documento/dc_72f331dd3bb9

How to cite

XYZFlow:Scaling Multi dimensional Shortcut Flows for Efficient Generative Modeling — arXiv:2608.12276 — arXiv (en), https://arxiv.org/abs/2608.12276 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_72f331dd3bb9 (Metraipolis archive dc_72f331dd3bb9, sha256 f6201203d8441f008b19bec36609e510630a1ac30bab15320f2ffbb408df0f25)

BibTeX

@misc{dc72f331dd3bb9,
  title = {XYZFlow:Scaling Multi dimensional Shortcut Flows for Efficient Generative Modeling — arXiv:2608.12276},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12276},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_72f331dd3bb9; sha256 f6201203d8441f008b19bec36609e510630a1ac30bab15320f2ffbb408df0f25},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12276. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

High-fidelity image generation faces a trade-off between speed and quality. Diffusion models produce strong visuals but require costly iterative sampling. Existing efficient methods mainly distill pretrained models into few-step samplers, a challenging process that depends heavily on teacher-model quality. In this paper, we introduce XYZFlow, a framework that rethinks efficient generation through multidimensional scaling of flow matching. Unlike single-step mappings, XYZFlow enhances expressivity by making probability paths more identifiable and learnable through structured multidimensional conditioning. We view autoregressive modeling as implicit flow straightening, where richer context reduces trajectory ambiguity. XYZFlow realizes this idea through two orthogonal dimensions: temporal scaling, which uses non-Markovian conditioning on the full denoising history; and spatial scaling, enabled by Next Shortcut Prediction, which sequentially generates patches using preceding patches' denoising trajectories as priors. Experiments show that XYZFlow achieves state-of-the-art performance, with 7.2-8.5X teacher speedups and competitive FID, while Next Shortcut Prediction delivers superior quality-latency trade-offs over model scaling or step reduction.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-13 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.12276 — 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 2026-10-19T05:42:25.926Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).