Metraipolis › archive › dc_63ea90e7a114
CAT-Flow: Curvature-Adaptive sTeps for Flow Matching — arXiv:2609.01746
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01746
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T04:59:19.657Z
- SHA-256 of the archived text
d46076bd20d05e4b9227896f4aa684e768592b5d21b1cd98f9aa07ce18ea6d76- Stable URL of this page
https://metraipolis.com/documento/dc_63ea90e7a114
How to cite
CAT-Flow: Curvature-Adaptive sTeps for Flow Matching — arXiv:2609.01746 — arXiv (en), https://arxiv.org/abs/2609.01746 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_63ea90e7a114 (Metraipolis archive dc_63ea90e7a114, sha256 d46076bd20d05e4b9227896f4aa684e768592b5d21b1cd98f9aa07ce18ea6d76)
BibTeX
@misc{dc63ea90e7a114,
title = {CAT-Flow: Curvature-Adaptive sTeps for Flow Matching — arXiv:2609.01746},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01746},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_63ea90e7a114; sha256 d46076bd20d05e4b9227896f4aa684e768592b5d21b1cd98f9aa07ce18ea6d76},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01746. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Flow Matching has emerged as a leading framework for generative modeling, powering state-of-the-art systems such as FLUX and Stable Diffusion 3.5. However, the iterative nature of its ODE-based sampling process creates a fundamental efficiency bottleneck: the quality of generated samples is highly sensitive to the choice of step-sizes, and current models typically require 20 to 30 steps for good quality. In this work, we propose two lightweight, training-free algorithms, CAT-OV and CAT-OT that adapt step-sizes at inference time based on a novel connection between Flow Matching sampling and gradient flow. Our algorithms are computed efficiently by not requiring additional neural function evaluations. Specifically, CAT-OT estimates curvature over time via a finite-difference approximation of the time-derivative of the vector field, while CAT-OV approximates curvature over the state space via a gradient of the vector field. Under suitable conditions, both methods have truncation error bounds of constant order. Empirically, CAT-OV and CAT-OT outperform existing step-size heuristics in image quality metrics across four text- to-image Flow Matching models, reducing the number of generation steps required to reach comparable quality by up to 40%. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.01746 — 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 2026-10-17T04:09:43.288Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).