Metraipolis › archive › dc_810d57b2403e
ReAL: Accelerating Flow Matching through Segment Advancement with Shared Lookahead — arXiv:2609.33202
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33202
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:51:26.662Z
- SHA-256 of the archived text
d50e2f4c25d7fd1338dae479423848ad1456960683c97376fbbc2d44f8161369- Stable URL of this page
https://metraipolis.com/documento/dc_810d57b2403e
How to cite
ReAL: Accelerating Flow Matching through Segment Advancement with Shared Lookahead — arXiv:2609.33202 — arXiv (en), https://arxiv.org/abs/2609.33202 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_810d57b2403e (Metraipolis archive dc_810d57b2403e, sha256 d50e2f4c25d7fd1338dae479423848ad1456960683c97376fbbc2d44f8161369)
BibTeX
@misc{dc810d57b2403e,
title = {ReAL: Accelerating Flow Matching through Segment Advancement with Shared Lookahead — arXiv:2609.33202},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33202},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_810d57b2403e; sha256 d50e2f4c25d7fd1338dae479423848ad1456960683c97376fbbc2d44f8161369},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33202. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Flow-matching models generate high-quality images and videos, but repeated neural network evaluations make sampling expensive. Skipping evaluations reduces this cost by extending an available velocity estimate over a longer span. However, local velocity agreement alone does not determine a suitable span, and checking each candidate endpoint adds costly model calls. We introduce ReAL, a training-free sampler that selects how far to advance using one shared lookahead. Our key insight is that the discrepancy between uncorrected and lookahead-corrected endpoint proposals can be computed directly from the observed velocity mismatch and the candidate span beyond the lookahead. This relation provides a span-dependent selection criterion without additional endpoint evaluations. The same lookahead selects the longest passing candidate span, corrects the accepted update, and supplies its velocity as the next starting estimate. After initialization, each regular iteration requires only one fresh evaluation. ReAL uses the pretrained velocity output and original noise schedule, with no additional training or access to internal features. Experiments cover four image-generation backbones, video generation, and image editing. ReAL achieves 4.91x measured speedup on FLUX.1-dev while retaining 97.0% of dense mean ImageReward. On HunyuanVideo, it achieves a 5.49x speedup while maintaining a VBench score close to that of dense sampling. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.33202 — 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 2026-10-07T23:29:27.161Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).