Iterative Flow Matching: Path Correction and Gradual Refinement for Enhanced Generative Modeling
SIAM Journal on Scientific Computing · 31.08.2026 · 48 (4) · C814-C831
DOI: 10.1137/25m1736633 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Scientific Computing, online erschienen am 20.07.2026. Verfasst von Eldad Haber und 4 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben.
Abstract (Originalsprache)
Generative models for image generation are now commonly used for a wide variety of applications, ranging from guided image generation for entertainment to solving inverse problems. Nonetheless, training a generator is a nontrivial feat that requires fine-tuning and can lead to so-called hallucinations, that is, the generation of images that are unrealistic. In this work, we explore image generation using flow matching. We explain and demonstrate why flow matching can generate hallucinations, and we propose an iterative process to improve the generation process. Our iterative process can be integrated into virtually any generative modeling technique, thereby enhancing the performance and robustness of image synthesis systems.
Zitieren
APA
Haber, E., Ahamed, S., Siddiqui, M. S. R., Zakariaei, N., & Eliasof, M. (2026). Iterative Flow Matching: Path Correction and Gradual Refinement for Enhanced Generative Modeling. SIAM Journal on Scientific Computing, 48(4), C814-C831. https://doi.org/10.1137/25m1736633
Vancouver
Haber E, Ahamed S, Siddiqui MSR, Zakariaei N, Eliasof M. Iterative Flow Matching: Path Correction and Gradual Refinement for Enhanced Generative Modeling. SIAM Journal on Scientific Computing. 2026;48(4):C814-C831. doi:10.1137/25m1736633
BibTeX
@article{Haber2026,
author = {Haber, Eldad and Ahamed, Shadab and Siddiqui, Md. Shahriar Rahim and Zakariaei, Niloufar and Eliasof, Moshe},
title = {Iterative Flow Matching: Path Correction and Gradual Refinement for Enhanced Generative Modeling},
journal = {SIAM Journal on Scientific Computing},
year = {2026},
volume = {48},
number = {4},
pages = {C814--C831},
doi = {10.1137/25m1736633}
}
EUVIMED