ReflexFlow: Rethinking Learning Objective for Exposure Bias Alleviation in Flow Matching
Abstract
Despite tremendous recent progress, Flow Matching methods still suffer from exposure bias due to discrepancies in training and inference. This paper investigates the root causes of exposure bias in Flow Matching, including: (1) the model lacks generalization to biased inputs during training, and (2) insufficient low-frequency content captured during early denoising, leading to accumulated bias. Based on these insights, we propose ReflexFlow, a simple and effective reflexive refinement of the Flow Matching learning objective that dynamically corrects exposure bias. ReflexFlow consists of two components: (1) Anti-Drift Rectification (ADR), which reflexively adjusts prediction targets for biased inputs utilizing a redesigned loss under training-time scheduled sampling; and (2) Frequency Compensation (FC), which reflects on missing low-frequency components and compensates them by reweighting the loss using exposure bias. ReflexFlow is model-agnostic, compatible with all Flow Matching frameworks, and improves generation quality across datasets. Experiments on CIFAR-10, CelebA-64, and ImageNet-256 show that ReflexFlow outperforms prior approaches in mitigating exposure bias, achieving a 35.65% reduction in FID on CelebA-64.
Cite
@article{arxiv.2512.04904,
title = {ReflexFlow: Rethinking Learning Objective for Exposure Bias Alleviation in Flow Matching},
author = {Guanbo Huang and Jingjia Mao and Fanding Huang and Fengkai Liu and Xiangyang Luo and Yaoyuan Liang and Jiasheng Lu and Xiaoe Wang and Pei Liu and Ruiliu Fu and Shao-Lun Huang},
journal= {arXiv preprint arXiv:2512.04904},
year = {2026}
}
Comments
After careful consideration, we have decided to withdraw our submission for substantial revisions. We plan to significantly improve Section 4 and include more comprehensive experiments. These changes are necessary to ensure the paper's quality and rigor. We believe the revisions will strengthen the contribution and provide a more solid foundation for the results