Metraipolis › archive › dc_edcebfabdac0
Contextual Flow Matching: Adaptive Step Selection in Flow Models for Efficient Visual Generation — arXiv:2610.03202
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.03202
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T22:50:32.249Z
- SHA-256 of the archived text
f99c31b2ae4e66e7e6e92f0e81fb7eac035b36b8e5977d303abb25f8f90efb15- Stable URL of this page
https://metraipolis.com/documento/dc_edcebfabdac0
How to cite
Contextual Flow Matching: Adaptive Step Selection in Flow Models for Efficient Visual Generation — arXiv:2610.03202 — arXiv, https://arxiv.org/abs/2610.03202 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_edcebfabdac0 (Metraipolis archive dc_edcebfabdac0, sha256 f99c31b2ae4e66e7e6e92f0e81fb7eac035b36b8e5977d303abb25f8f90efb15)
BibTeX
@misc{dcedcebfabdac0,
title = {Contextual Flow Matching: Adaptive Step Selection in Flow Models for Efficient Visual Generation — arXiv:2610.03202},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.03202},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_edcebfabdac0; sha256 f99c31b2ae4e66e7e6e92f0e81fb7eac035b36b8e5977d303abb25f8f90efb15},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03202. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Flow Matching enables high-quality visual generation via continuous-time dynamics, but inference remains costly due to multiple sequential function evaluations. Existing acceleration methods reduce the number of function evaluations but often introduce additional training overhead, degrade quality, or fail to account for input-dependent variability. We propose COFLOW, an inference-time method that adaptively selects the step counts each generation based on the prompt features. Our context-aware COFLOW is trained online with an unsupervised reward that balances inference efficiency and generation fidelity. Our method is plug-and-play, requiring no retraining of the underlying generative model. It generalizes to image and video generation, achieving over 2.5x speedup while preserving perceptual and semantic quality. We further provide a theoretical analysis establishing an O(1/K) forward-Euler discretization error bound under standard regularity conditions. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.03202 — 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 2026-10-05T22:45:55.841Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).